{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T10:25:45Z","timestamp":1779877545446,"version":"3.53.1"},"reference-count":121,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T00:00:00Z","timestamp":1744761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T00:00:00Z","timestamp":1744761600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s11263-025-02426-2","type":"journal-article","created":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T05:58:01Z","timestamp":1744783081000},"page":"5238-5261","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["D3T: Dual-Domain Diffusion Transformer in Triplanar Latent Space for 3D Incomplete-View CT Reconstruction"],"prefix":"10.1007","volume":"133","author":[{"given":"Xuhui","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yawen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiantong","family":"Zhen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baochang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,16]]},"reference":[{"key":"2426_CR1","doi-asserted-by":"publisher","first-page":"179424","DOI":"10.1109\/ACCESS.2020.3026658","volume":"8","author":"A Abdollahi","year":"2020","unstructured":"Abdollahi, A., Pradhan, B., & Alamri, A. (2020). Vnet: An end-to-end fully convolutional neural network for road extraction from high-resolution remote sensing data. IEEE Access, 8, 179424\u2013179436.","journal-title":"IEEE Access"},{"issue":"10","key":"2426_CR2","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1145\/2001269.2001293","volume":"54","author":"S Agarwal","year":"2011","unstructured":"Agarwal, S., Furukawa, Y., Snavely, N., et al. (2011). Building Rome in a day. Communications of the ACM, 54(10), 105\u2013112.","journal-title":"Communications of the ACM"},{"issue":"2","key":"2426_CR3","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1118\/1.3528204","volume":"38","author":"SG Armato III","year":"2011","unstructured":"Armato, S. G., III., McLennan, G., Bidaut, L., et al. (2011). The lung image database consortium (LIDC) and image database resource initiative (IDRI): A completed reference database of lung nodules on CT scans. Medical Physics, 38(2), 915\u2013931.","journal-title":"Medical Physics"},{"key":"2426_CR4","doi-asserted-by":"crossref","unstructured":"Barron, J. T., Mildenhall, B., Tancik, M., et\u00a0al. (2021). Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 5855\u20135864).","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"2426_CR5","doi-asserted-by":"crossref","unstructured":"Blattmann, A., Rombach, R., Ling, H., et\u00a0al. (2023). Align your latents: High-resolution video synthesis with latent diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 22563\u201322575).","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"2426_CR6","doi-asserted-by":"crossref","unstructured":"Cao, Z., Hong, F., Wu, T., et\u00a0al. (2025). Difftf++: 3d-aware diffusion transformer for large-vocabulary 3D generation. IEEE Transactions on Pattern Analysis and Machine Intelligence.","DOI":"10.1109\/TPAMI.2025.3528247"},{"key":"2426_CR7","doi-asserted-by":"crossref","unstructured":"Chan, E. R., Lin, C. Z., Chan, M. A., et\u00a0al. (2022). Efficient geometry-aware 3D generative adversarial networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16123\u201316133).","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"2426_CR8","unstructured":"Chang, A. X., Funkhouser, T., Guibas, L., et\u00a0al. (2015). Shapenet: An information-rich 3D model repository. arXiv:1512.03012"},{"key":"2426_CR9","doi-asserted-by":"crossref","unstructured":"Chen, A., Xu, Z., Zhao, F., et\u00a0al. (2021). Mvsnerf: Fast generalizable radiance field reconstruction from multi-view stereo. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 14124\u201314133).","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"2426_CR10","doi-asserted-by":"crossref","unstructured":"Chen, A., Xu, Z., Geiger, A., et\u00a0al. (2022). Tensorf: Tensorial radiance fields. In: European conference on computer vision (pp. 333\u2013350). Springer.","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"2426_CR11","doi-asserted-by":"crossref","unstructured":"Chen, D. Z., Siddiqui, Y., Lee, H. Y., et\u00a0al. (2023a). Text2tex: Text-driven texture synthesis via diffusion models. In: Proceedings of the IEEE\/CVF international conference on computer vision (pp. 18558\u201318568).","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"2426_CR12","doi-asserted-by":"crossref","unstructured":"Chen, H., Gu, J., Chen, A., et\u00a0al. (2023b). Single-stage diffusion nerf: A unified approach to 3d generation and reconstruction. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 2416\u20132425).","DOI":"10.1109\/ICCV51070.2023.00229"},{"key":"2426_CR13","unstructured":"Chen, J., Yu, J., Ge, C., et\u00a0al. (2023c). Pixart-$$alpha$$: Fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv:2310.00426"},{"key":"2426_CR14","doi-asserted-by":"crossref","unstructured":"Chen, R., Chen, Y., Jiao, N., et\u00a0al. (2023d). Fantasia3d: Disentangling geometry and appearance for high-quality text-to-3d content creation. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 22246\u201322256).","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"2426_CR15","first-page":"25683","volume":"35","author":"H Chung","year":"2022","unstructured":"Chung, H., Sim, B., Ryu, D., et al. (2022). Improving diffusion models for inverse problems using manifold constraints. Advances in Neural Information Processing Systems, 35, 25683\u201325696.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2426_CR16","unstructured":"Chung, H., Lee, S., Ye, J. C. (2023a). Decomposed diffusion sampler for accelerating large-scale inverse problems. arXiv:2303.05754"},{"key":"2426_CR17","doi-asserted-by":"crossref","unstructured":"Chung, H., Ryu, D., McCann, M. T., et\u00a0al. (2023b). Solving 3D inverse problems using pre-trained 2D diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 22542\u201322551).","DOI":"10.1109\/CVPR52729.2023.02159"},{"key":"2426_CR18","unstructured":"Deng, Y., Wang, C., Hui, Y., et\u00a0al. (2021). Ctspine1k: A large-scale dataset for spinal vertebrae segmentation in computed tomography. arXiv:2105.14711"},{"key":"2426_CR19","unstructured":"Du, C., Lin, X., Wu, Q., et\u00a0al. (2024). Dper: Diffusion prior driven neural representation for limited angle and sparse view CT reconstruction. arXiv:2404.17890"},{"key":"2426_CR20","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B. (2021). Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 12873\u201312883).","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"2426_CR21","unstructured":"Gao, P., Zhuo, L., Liu, D., et\u00a0al. (2024). Lumina-t2x: Transforming text into any modality, resolution, and duration via flow-based large diffusion transformers. arXiv:2405.05945"},{"key":"2426_CR22","doi-asserted-by":"crossref","unstructured":"Gao, S., Liu, X., Zeng, B., et\u00a0al. (2023). Implicit diffusion models for continuous super-resolution. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10021\u201310030).","DOI":"10.1109\/CVPR52729.2023.00966"},{"key":"2426_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107680","volume":"236","author":"R Ge","year":"2022","unstructured":"Ge, R., He, Y., Xia, C., et al. (2022). X-CTRSNET: 3D cervical vertebra CT reconstruction and segmentation directly from 2D X-ray images. Knowledge-Based Systems, 236, 107680.","journal-title":"Knowledge-Based Systems"},{"key":"2426_CR24","doi-asserted-by":"crossref","unstructured":"Gieruc, T., K\u00e4stingsch\u00e4fer, M., Bernhard, S., et\u00a0al. (2024). 6img-to-3d: Few-image large-scale outdoor driving scene reconstruction. arXiv:2404.12378","DOI":"10.1109\/IV64158.2025.11097387"},{"key":"2426_CR25","unstructured":"Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., et\u00a0al. (2014). Generative adversarial nets. In Advances in neural information processing systems (Vol. 27)."},{"key":"2426_CR26","doi-asserted-by":"crossref","unstructured":"Gu, S., Chen, D., Bao, J., et\u00a0al. (2022). Vector quantized diffusion model for text-to-image synthesis. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10696\u201310706).","DOI":"10.1109\/CVPR52688.2022.01043"},{"issue":"1","key":"2426_CR27","doi-asserted-by":"publisher","first-page":"4080","DOI":"10.1038\/s41467-020-17971-2","volume":"11","author":"SA Harmon","year":"2020","unstructured":"Harmon, S. A., Sanford, T. H., Xu, S., et al. (2020). Artificial intelligence for the detection of covid-19 pneumonia on chest CT using multinational datasets. Nature Communications, 11(1), 4080.","journal-title":"Nature Communications"},{"key":"2426_CR28","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., Nath, V., Tang, Y., et\u00a0al. (2021). Swin unetr: Swin transformers for semantic segmentation of brain tumors in MRI images. In International MICCAI brainlesion workshop (pp. 272\u2013284). Springer.","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"2426_CR29","unstructured":"He, J., Li, B., Yang, G., et\u00a0al. (2024). Blaze3dm: Marry triplane representation with diffusion for 3D medical inverse problem solving. arXiv:2405.15241"},{"key":"2426_CR30","doi-asserted-by":"crossref","unstructured":"Henry, A., Dachapally, P. R., Pawar, S., et\u00a0al. (2020). Query-key normalization for transformers. arXiv:2010.04245","DOI":"10.18653\/v1\/2020.findings-emnlp.379"},{"key":"2426_CR31","doi-asserted-by":"crossref","unstructured":"Henzler, P., Rasche, V., Ropinski, T., et\u00a0al. (2018). Single-image tomography: 3D volumes from 2D cranial x-rays. In Computer graphics forum (pp. 377\u2013388). Wiley Online Library.","DOI":"10.1111\/cgf.13369"},{"key":"2426_CR32","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84628-723-7","volume-title":"Fundamentals of computerized tomography: Image reconstruction from projections","author":"GT Herman","year":"2009","unstructured":"Herman, G. T. (2009). Fundamentals of computerized tomography: Image reconstruction from projections. Springer."},{"key":"2426_CR33","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., et\u00a0al. (2017). Gans trained by a two time-scale update rule converge to a local nash equilibrium. In Advances in neural information processing systems (Vol. 30)."},{"key":"2426_CR34","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33, 6840\u20136851.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2426_CR35","unstructured":"Ho, J., Chan, W., Saharia, C., et\u00a0al. (2022a). Imagen video: High definition video generation with diffusion models. arXiv:2210.02303"},{"key":"2426_CR36","first-page":"8633","volume":"35","author":"J Ho","year":"2022","unstructured":"Ho, J., Salimans, T., Gritsenko, A., et al. (2022). Video diffusion models. Advances in Neural Information Processing Systems, 35, 8633\u20138646.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2426_CR37","unstructured":"Hong, Y., Zhang, K., Gu, J., et\u00a0al. (2023). LRM: Large reconstruction model for single image to 3D. arXiv:2311.04400"},{"key":"2426_CR38","doi-asserted-by":"crossref","unstructured":"Hu, Z., Zhao, M., Zhao, C., et\u00a0al. (2024). Efficientdreamer: high-fidelity and robust 3d creation via orthogonal-view diffusion priors. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4949\u20134958).","DOI":"10.1109\/CVPR52733.2024.00473"},{"issue":"4","key":"2426_CR39","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1109\/TRPMS.2018.2824400","volume":"2","author":"Y Huang","year":"2018","unstructured":"Huang, Y., Taubmann, O., Huang, X., et al. (2018). Scale-space anisotropic total variation for limited angle tomography. IEEE Transactions on Radiation and Plasma Medical Sciences, 2(4), 307\u2013314.","journal-title":"IEEE Transactions on Radiation and Plasma Medical Sciences"},{"key":"2426_CR40","doi-asserted-by":"crossref","unstructured":"Huang, Y., Preuhs, A., Lauritsch, G., et\u00a0al. (2019). Data consistent artifact reduction for limited angle tomography with deep learning prior. In International workshop on machine learning for medical image reconstruction (pp. 101\u2013112). Springer.","DOI":"10.1007\/978-3-030-33843-5_10"},{"key":"2426_CR41","doi-asserted-by":"crossref","unstructured":"Jiang, L., Zhang, M., Wei, R., et\u00a0al. (2021). Reconstruction of 3D CT from a single x-ray projection view using CVAE-GAN. In 2021 IEEE international conference on medical imaging physics and engineering (ICMIPE) (pp. 1\u20136). IEEE.","DOI":"10.1109\/ICMIPE53131.2021.9698875"},{"issue":"9","key":"2426_CR42","doi-asserted-by":"publisher","first-page":"4509","DOI":"10.1109\/TIP.2017.2713099","volume":"26","author":"KH Jin","year":"2017","unstructured":"Jin, K. H., McCann, M. T., Froustey, E., et al. (2017). Deep convolutional neural network for inverse problems in imaging. IEEE Transactions on Image Processing, 26(9), 4509\u20134522.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"1","key":"2426_CR43","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","volume":"6","author":"AE Johnson","year":"2019","unstructured":"Johnson, A. E., Pollard, T. J., Berkowitz, S. J., et al. (2019). MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Scientific Data, 6(1), 317.","journal-title":"Scientific Data"},{"issue":"12","key":"2426_CR44","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1056\/NEJMoa0800996","volume":"359","author":"CD Johnson","year":"2008","unstructured":"Johnson, C. D., Chen, M. H., Toledano, A. Y., et al. (2008). Accuracy of CT colonography for detection of large adenomas and cancers. New England Journal of Medicine, 359(12), 1207\u20131217.","journal-title":"New England Journal of Medicine"},{"key":"2426_CR45","unstructured":"Jun, H., Nichol, A. (2023). Shap-E: Generating conditional 3D implicit functions. arXiv:2305.02463"},{"key":"2426_CR46","doi-asserted-by":"crossref","unstructured":"Kasten, Y., Doktofsky, D., Kovler, I. (2020). End-to-end convolutional neural network for 3D reconstruction of knee bones from bi-planar X-ray images. In Machine learning for medical image reconstruction: third international workshop, MLMIR 2020, held in conjunction with MICCAI 2020, Lima, Peru, October 8, 2020, Proceedings 3 (pp. 123\u2013133). Springer.","DOI":"10.1007\/978-3-030-61598-7_12"},{"key":"2426_CR47","doi-asserted-by":"publisher","first-page":"1613","DOI":"10.1007\/s00330-012-2452-z","volume":"22","author":"M Katsura","year":"2012","unstructured":"Katsura, M., Matsuda, I., Akahane, M., et al. (2012). Model-based iterative reconstruction technique for radiation dose reduction in chest CT: Comparison with the adaptive statistical iterative reconstruction technique. European Radiology, 22, 1613\u20131623.","journal-title":"European Radiology"},{"key":"2426_CR48","unstructured":"Kong, Z., Ping, W., Huang, J., et\u00a0al. (2020). Diffwave: A versatile diffusion model for audio synthesis. arXiv:2009.09761"},{"key":"2426_CR49","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (Vol. 25)."},{"key":"2426_CR50","doi-asserted-by":"crossref","unstructured":"Lee, S., Chung, H., Park, M., et\u00a0al. (2023). Improving 3D imaging with pre-trained perpendicular 2D diffusion models. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 10710\u201310720).","DOI":"10.1109\/ICCV51070.2023.00983"},{"key":"2426_CR51","unstructured":"Li, J., Tan, H., Zhang, K., et\u00a0al. (2023). Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model. arXiv:2311.06214"},{"key":"2426_CR52","doi-asserted-by":"crossref","unstructured":"Lin, C. H., Gao, J., Tang, L., et\u00a0al.: (2023a) Magic3d: High-resolution text-to-3d content creation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 300\u2013309).","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"2426_CR53","doi-asserted-by":"crossref","unstructured":"Lin, K. E., Lin, Y. C., Lai, W. S., et\u00a0al. (2023b). Vision transformer for nerf-based view synthesis from a single input image. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision (pp. 806\u2013815).","DOI":"10.1109\/WACV56688.2023.00087"},{"key":"2426_CR54","doi-asserted-by":"crossref","unstructured":"Lin, W. A., Liao, H., Peng, C., et\u00a0al. (2019). Dudonet: Dual domain network for CT metal artifact reduction. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10512\u201310521).","DOI":"10.1109\/CVPR.2019.01076"},{"key":"2426_CR55","doi-asserted-by":"crossref","unstructured":"Liu, J., Li, C., Ren, Y., et\u00a0al. (2022a). Diffsinger: Singing voice synthesis via shallow diffusion mechanism. In Proceedings of the AAAI conference on artificial intelligence (pp. 11020\u201311028).","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"2426_CR56","doi-asserted-by":"crossref","unstructured":"Liu, J., Anirudh, R., Thiagarajan, J. J., et\u00a0al. (2023a). Dolce: A model-based probabilistic diffusion framework for limited-angle CT reconstruction. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 10498\u201310508).","DOI":"10.1109\/ICCV51070.2023.00963"},{"issue":"2","key":"2426_CR57","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.jmir.2014.02.002","volume":"45","author":"L Liu","year":"2014","unstructured":"Liu, L. (2014). Model-based iterative reconstruction: A promising algorithm for today\u2019s computed tomography imaging. Journal of Medical Imaging and Radiation Sciences, 45(2), 131\u2013136.","journal-title":"Journal of Medical Imaging and Radiation Sciences"},{"key":"2426_CR58","first-page":"22226","volume":"36","author":"M Liu","year":"2023","unstructured":"Liu, M., Xu, C., Jin, H., et al. (2023). One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimization. Advances in Neural Information Processing Systems, 36, 22226\u201322246.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2426_CR59","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1007\/s11548-021-02363-8","volume":"16","author":"P Liu","year":"2021","unstructured":"Liu, P., Han, H., Du, Y., et al. (2021). Deep learning to segment pelvic bones: Large-scale CT datasets and baseline models. International Journal of Computer Assisted Radiology and Surgery, 16, 749\u2013756.","journal-title":"International Journal of Computer Assisted Radiology and Surgery"},{"key":"2426_CR60","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van\u00a0Hoorick, B., et\u00a0al. (2023c). Zero-1-to-3: Zero-shot one image to 3D object. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 9298\u20139309).","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"2426_CR61","doi-asserted-by":"crossref","unstructured":"Liu, X., Qiao, Z., Liu, R., et\u00a0al. (2024). Diffux2ct: Diffusion learning to reconstruct CT images from biplanar x-rays. In European conference on computer vision (pp. 458\u2013476). Springer.","DOI":"10.1007\/978-3-031-72775-7_26"},{"issue":"23","key":"2426_CR62","doi-asserted-by":"publisher","first-page":"7923","DOI":"10.1088\/0031-9155\/57\/23\/7923","volume":"57","author":"Y Liu","year":"2012","unstructured":"Liu, Y., Ma, J., Fan, Y., et al. (2012). Adaptive-weighted total variation minimization for sparse data toward low-dose X-ray computed tomography image reconstruction. Physics in Medicine & Biology, 57(23), 7923.","journal-title":"Physics in Medicine & Biology"},{"key":"2426_CR63","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., et\u00a0al. (2022b). Video swin transformer. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3202\u20133211).","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"2426_CR64","doi-asserted-by":"crossref","unstructured":"Long, X., Guo, Y. C., Lin, C., et\u00a0al. (2024). Wonder3d: Single image to 3d using cross-domain diffusion. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9970\u20139980).","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"2426_CR65","unstructured":"Ma, C., Li, Z., He, J., et\u00a0al. (2023a). Universal incomplete-view CT reconstruction with prompted contextual transformer. arXiv:2312.07846"},{"key":"2426_CR66","doi-asserted-by":"crossref","unstructured":"Ma, C., Li, Z., Zhang, J., et\u00a0al. (2023b). Freeseed: Frequency-band-aware and self-guided network for sparse-view CT reconstruction. In International conference on medical image computing and computer-assisted intervention (pp. 250\u2013259). Springer.","DOI":"10.1007\/978-3-031-43999-5_24"},{"issue":"1","key":"2426_CR67","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P. P., Tancik, M., et al. (2021). Nerf: Representing scenes as neural radiance fields for view synthesis. Communications of the ACM, 65(1), 99\u2013106.","journal-title":"Communications of the ACM"},{"issue":"2","key":"2426_CR68","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/TCI.2015.2431913","volume":"1","author":"KA Mohan","year":"2015","unstructured":"Mohan, K. A., Venkatakrishnan, S., Gibbs, J. W., et al. (2015). Timbir: A method for time-space reconstruction from interlaced views. IEEE Transactions on Computational Imaging, 1(2), 96\u2013111.","journal-title":"IEEE Transactions on Computational Imaging"},{"issue":"4","key":"2426_CR69","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530127","volume":"41","author":"T M\u00fcller","year":"2022","unstructured":"M\u00fcller, T., Evans, A., Schied, C., et al. (2022). Instant neural graphics primitives with a multiresolution hash encoding. ACM Transactions on Graphics (TOG), 41(4), 1\u201315.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2426_CR70","unstructured":"Nichol, A., Dhariwal, P., Ramesh, A., et\u00a0al. (2021). Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv:2112.10741"},{"key":"2426_CR71","unstructured":"Nolan, T. (2022). Head-and-neck squamous cell carcinoma patients with CT taken during pre-treatment, mid-treatment, and post-treatment (HNSCC-3DCT-RT). Cancer Imaging Archive."},{"key":"2426_CR72","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S. (2023). Scalable diffusion models with transformers. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 4195\u20134205).","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"2426_CR73","doi-asserted-by":"crossref","unstructured":"Peng, W., Adeli, E., Bosschieter, T., et\u00a0al. (2023). Generating realistic brain MRIs via a conditional diffusion probabilistic model. In: International conference on medical image computing and computer-assisted intervention (pp. 14\u201324). Springer.","DOI":"10.1007\/978-3-031-43993-3_2"},{"key":"2426_CR74","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De\u00a0Vries, H., et\u00a0al, (2018). Film: Visual reasoning with a general conditioning layer. In Proceedings of the AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"2426_CR75","unstructured":"Poole, B., Jain, A., Barron, J. T., et\u00a0al. (2022). Dreamfusion: Text-to-3d using 2d diffusion. arXiv:2209.14988"},{"key":"2426_CR76","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., et\u00a0al. (2022). Hierarchical text-conditional image generation with clip latents 1(2):3. arXiv:2204.06125"},{"key":"2426_CR77","doi-asserted-by":"crossref","unstructured":"Ren, Y., Wang, F., Zhang, T., et\u00a0al. (2023). Volrecon: Volume rendering of signed ray distance functions for generalizable multi-view reconstruction. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16685\u201316695).","DOI":"10.1109\/CVPR52729.2023.01601"},{"key":"2426_CR78","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., et\u00a0al. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10684\u201310695).","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2426_CR79","unstructured":"Ronchetti, M. (2020). Torchradon: Fast differentiable routines for computed tomography. arXiv:2009.14788"},{"key":"2426_CR80","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Chan, W., Saxena, S., et al. (2022). Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, 35, 36479\u201336494.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"2426_CR81","first-page":"4713","volume":"45","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Ho, J., Chan, W., et al. (2022). Image super-resolution via iterative refinement. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4), 4713\u20134726.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2426_CR82","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J. L., Zheng, E., Frahm, J. M., et\u00a0al. (2016). Pixelwise view selection for unstructured multi-view stereo. In Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part III 14 (pp. 501\u2013518). Springer.","DOI":"10.1007\/978-3-319-46487-9_31"},{"issue":"11","key":"2426_CR83","doi-asserted-by":"publisher","first-page":"880","DOI":"10.1038\/s41551-019-0466-4","volume":"3","author":"L Shen","year":"2019","unstructured":"Shen, L., Zhao, W., & Xing, L. (2019). Patient-specific reconstruction of volumetric computed tomography images from a single projection view via deep learning. Nature Biomedical Engineering, 3(11), 880\u2013888.","journal-title":"Nature Biomedical Engineering"},{"key":"2426_CR84","unstructured":"Shi, Y., Wang, P., Ye, J., et\u00a0al. (2023). Mvdream: Multi-view diffusion for 3d generation. arXiv:2308.16512"},{"issue":"1","key":"2426_CR85","doi-asserted-by":"publisher","first-page":"15249","DOI":"10.1038\/s41598-021-94634-2","volume":"11","author":"R Shiode","year":"2021","unstructured":"Shiode, R., Kabashima, M., Hiasa, Y., et al. (2021). 2d\u20133d reconstruction of distal forearm bone from actual X-ray images of the wrist using convolutional neural networks. Scientific Reports, 11(1), 15249.","journal-title":"Scientific Reports"},{"key":"2426_CR86","first-page":"121859","volume":"37","author":"W Shuang","year":"2024","unstructured":"Shuang, W., Lin, Y., Zeng, Y., et al. (2024). Direct3d: Scalable image-to-3D generation via 3D latent diffusion transformer. Advances in Neural Information Processing Systems, 37, 121859\u2013121881.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"2426_CR87","doi-asserted-by":"publisher","first-page":"657","DOI":"10.21037\/jss.2017.12.05","volume":"3","author":"ID Siasios","year":"2017","unstructured":"Siasios, I. D., Pollina, J., Khan, A., et al. (2017). Percutaneous screw placement in the lumbar spine with a modified guidance technique based on 3D CT navigation system. Journal of Spine Surgery, 3(4), 657.","journal-title":"Journal of Spine Surgery"},{"key":"2426_CR88","unstructured":"Simpson, A. L., Antonelli, M., Bakas, S., et\u00a0al. (2019). A large annotated medical image dataset for the development and evaluation of segmentation algorithms. arXiv:1902.09063"},{"key":"2426_CR89","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., et\u00a0al. (2015). Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning (pp. 2256\u20132265). PMLR."},{"key":"2426_CR90","unstructured":"Song, J., Meng, C., Ermon, S. (2020). Denoising diffusion implicit models. arXiv:2010.02502"},{"key":"2426_CR91","unstructured":"Song, Y., Shen, L., Xing, L., et\u00a0al. (2021). Solving inverse problems in medical imaging with score-based generative models. arXiv:2111.08005"},{"key":"2426_CR92","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., et al. (2024). Roformer: Enhanced transformer with rotary position embedding. Neurocomputing, 568, 127063.","journal-title":"Neurocomputing"},{"key":"2426_CR93","doi-asserted-by":"crossref","unstructured":"Tang, J., Wang, T., Zhang, B., et\u00a0al. (2023). Make-it-3D: High-fidelity 3D creation from a single image with diffusion prior. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 22819\u201322829).","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"2426_CR94","doi-asserted-by":"crossref","unstructured":"Trevithick, A., Yang, B. (2021). GRF: Learning a general radiance field for 3d representation and rendering. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 15182\u201315192).","DOI":"10.1109\/ICCV48922.2021.01490"},{"issue":"11","key":"2426_CR95","doi-asserted-by":"publisher","first-page":"4532","DOI":"10.1109\/TIP.2013.2277784","volume":"22","author":"SV Venkatakrishnan","year":"2013","unstructured":"Venkatakrishnan, S. V., Drummy, L. F., Jackson, M. A., et al. (2013). A model based iterative reconstruction algorithm for high angle annular dark field-scanning transmission electron microscope (HAADF-STEM) tomography. IEEE Transactions on Image Processing, 22(11), 4532\u20134544.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"1","key":"2426_CR96","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/MSP.2021.3123594","volume":"39","author":"SV Venkatakrishnan","year":"2021","unstructured":"Venkatakrishnan, S. V., Mohan, K. A., Ziabari, A. K., et al. (2021). Algorithm-driven advances for scientific CT instruments: From model-based to deep learning-based approaches. IEEE Signal Processing Magazine, 39(1), 32\u201343.","journal-title":"IEEE Signal Processing Magazine"},{"key":"2426_CR97","doi-asserted-by":"crossref","unstructured":"Wang, C., Shang, K., Zhang, H., et\u00a0al. (2022a). Dudotrans: dual-domain transformer for sparse-view CT reconstruction. In International workshop on machine learning for medical image reconstruction (pp. 84\u201394). Springer.","DOI":"10.1007\/978-3-031-17247-2_9"},{"issue":"6","key":"2426_CR98","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1109\/TMI.2018.2833635","volume":"37","author":"G Wang","year":"2018","unstructured":"Wang, G., Ye, J. C., Mueller, K., et al. (2018). Image reconstruction is a new frontier of machine learning. IEEE Transactions on Medical Imaging, 37(6), 1289\u20131296.","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"12","key":"2426_CR99","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1038\/s42256-020-00273-z","volume":"2","author":"G Wang","year":"2020","unstructured":"Wang, G., Ye, J. C., & De Man, B. (2020). Deep learning for tomographic image reconstruction. Nature Machine Intelligence, 2(12), 737\u2013748.","journal-title":"Nature Machine Intelligence"},{"key":"2426_CR100","doi-asserted-by":"crossref","unstructured":"Wang, H., Du, X., Li, J., et\u00a0al. (2023a). Score Jacobian chaining: Lifting pretrained 2D diffusion models for 3d generation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 12619\u201312629).","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"2426_CR101","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wang, Z., Genova, K., et\u00a0al. (2021). IBRNet: Learning multi-view image-based rendering. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4690\u20134699).","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"2426_CR102","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhang, B., Zhang, T., et\u00a0al. (2023b). Rodin: A generative model for sculpting 3d digital avatars using diffusion. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4563\u20134573).","DOI":"10.1109\/CVPR52729.2023.00443"},{"issue":"4","key":"2426_CR103","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A. C., Sheikh, H. R., et al. (2004). Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4), 600\u2013612.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2426_CR104","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D., et\u00a0al. (2022b). Medclip: Contrastive learning from unpaired medical images and text. In Proceedings of the conference on empirical methods in natural language processing. Conference on empirical methods in natural language processing (p. 3876).","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"2426_CR105","first-page":"8406","volume":"36","author":"Z Wang","year":"2023","unstructured":"Wang, Z., Lu, C., Wang, Y., et al. (2023). ProlificDreamer: High-fidelity and diverse text-to-3D generation with variational score distillation. Advances in Neural Information Processing Systems, 36, 8406\u20138441.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2426_CR106","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, Y., Chen, Y., et\u00a0al. (2024). CRM: Single image to 3D textured mesh with convolutional reconstruction model. In European conference on computer vision (pp. 57\u201374). Springer.","DOI":"10.1007\/978-3-031-72751-1_4"},{"issue":"1","key":"2426_CR107","doi-asserted-by":"publisher","first-page":"016001","DOI":"10.1117\/1.JMI.8.1.016001","volume":"8","author":"J Wu","year":"2021","unstructured":"Wu, J., & Mahfouz, M. R. (2021). Reconstruction of knee anatomy from single-plane fluoroscopic X-ray based on a nonlinear statistical shape model. Journal of Medical Imaging, 8(1), 016001\u2013016001.","journal-title":"Journal of Medical Imaging"},{"key":"2426_CR108","doi-asserted-by":"crossref","unstructured":"Wu, J. Z., Ge, Y., Wang, X., et\u00a0al. (2023). Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 7623\u20137633).","DOI":"10.1109\/ICCV51070.2023.00701"},{"issue":"11","key":"2426_CR109","doi-asserted-by":"publisher","first-page":"3002","DOI":"10.1109\/TMI.2021.3078067","volume":"40","author":"W Wu","year":"2021","unstructured":"Wu, W., Hu, D., Niu, C., et al. (2021). Drone: Dual-domain residual-based optimization network for sparse-view CT reconstruction. IEEE Transactions on Medical Imaging, 40(11), 3002\u20133014.","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"4","key":"2426_CR110","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3658162","volume":"43","author":"Z Wu","year":"2024","unstructured":"Wu, Z., Li, Y., Yan, H., et al. (2024). Blockfusion: Expandable 3D scene generation using latent tri-plane extrapolation. ACM Transactions on Graphics (TOG), 43(4), 1\u201317.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2426_CR111","unstructured":"Xu, J., Cheng, W., Gao, Y., et\u00a0al. (2024). Instantmesh: Efficient 3D mesh generation from a single image with sparse-view large reconstruction models. arXiv:2404.07191"},{"key":"2426_CR112","doi-asserted-by":"crossref","unstructured":"Ying, X., Guo, H., Ma, K., et\u00a0al. (2019). X2CT-GAN: Reconstructing CT from biplanar X-rays with generative adversarial networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10619\u201310628).","DOI":"10.1109\/CVPR.2019.01087"},{"key":"2426_CR113","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., et\u00a0al. (2021). pixelnerf: Neural radiance fields from one or few images. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4578\u20134587).","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"2426_CR114","doi-asserted-by":"crossref","unstructured":"Yu, S., Sohn, K., Kim, S., et\u00a0al. (2023). Video probabilistic diffusion models in projected latent space. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 18456\u201318466).","DOI":"10.1109\/CVPR52729.2023.01770"},{"key":"2426_CR115","unstructured":"Zhang, B., & Sennrich, R. (2019). Root mean square layer normalization. In Advances in neural information processing systems (Vol. 32)."},{"issue":"8","key":"2426_CR116","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad3320","volume":"69","author":"C Zhang","year":"2024","unstructured":"Zhang, C., Liu, L., Dai, J., et al. (2024). XTransCT: Ultra-fast volumetric CT reconstruction using two orthogonal X-ray projections for image-guided radiation therapy via a transformer network. Physics in Medicine & Biology, 69(8), 085010.","journal-title":"Physics in Medicine & Biology"},{"key":"2426_CR117","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A. A., et\u00a0al. (2018a). The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 586\u2013595).","DOI":"10.1109\/CVPR.2018.00068"},{"issue":"6","key":"2426_CR118","doi-asserted-by":"publisher","first-page":"1407","DOI":"10.1109\/TMI.2018.2823338","volume":"37","author":"Z Zhang","year":"2018","unstructured":"Zhang, Z., Liang, X., Dong, X., et al. (2018). A sparse-view CT reconstruction method based on combination of DenseNet and deconvolution. IEEE Transactions on Medical Imaging, 37(6), 1407\u20131417.","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"2426_CR119","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Yu, L., Liang, X., et\u00a0al. (2021). TransCT: Dual-path transformer for low dose computed tomography. In Medical image computing and computer assisted intervention\u2013MICCAI 2021: 24th international conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part VI 24 (pp. 55\u201364). Springer.","DOI":"10.1007\/978-3-030-87231-1_6"},{"key":"2426_CR120","doi-asserted-by":"crossref","unstructured":"Zheng, X. Y., Pan, H., Guo, Y. X., et\u00a0al. (2024). Mvd$$\\hat{\\,}$$ 2: Efficient multiview 3D reconstruction for multiview diffusion. In ACM SIGGRAPH 2024 conference papers (pp. 1\u201311).","DOI":"10.1145\/3641519.3657403"},{"key":"2426_CR121","unstructured":"Zhu, J., Zhuang, P., & Koyejo, S. (2023). HiFA: High-fidelity text-to-3D generation with advanced diffusion guidance. arXiv:2305.18766"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02426-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02426-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02426-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T10:53:11Z","timestamp":1757155991000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02426-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,16]]},"references-count":121,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["2426"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02426-2","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,16]]},"assertion":[{"value":"1 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This work proposes a CT reconstruction method from incomplete-view data. It doesn\u2019t have a direct negative social impact, yet we should prevent its misuse for malicious intents.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}