{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T15:52:27Z","timestamp":1756309947853,"version":"3.40.3"},"publisher-location":"Cham","reference-count":88,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031732225"},{"type":"electronic","value":"9783031732232"}],"license":[{"start":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:00:00Z","timestamp":1731024000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:00:00Z","timestamp":1731024000000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73223-2_25","type":"book-chapter","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T18:48:56Z","timestamp":1731005336000},"page":"454-472","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["GOEmbed: Gradient Origin Embeddings for\u00a0Representation Agnostic 3D Feature Learning"],"prefix":"10.1007","author":[{"given":"Animesh","family":"Karnewar","sequence":"first","affiliation":[]},{"given":"Roman","family":"Shapovalov","sequence":"additional","affiliation":[]},{"given":"Tom","family":"Monnier","sequence":"additional","affiliation":[]},{"given":"Andrea","family":"Vedaldi","sequence":"additional","affiliation":[]},{"given":"Niloy J.","family":"Mitra","sequence":"additional","affiliation":[]},{"given":"David","family":"Novotny","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,8]]},"reference":[{"key":"25_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1007\/978-3-030-58542-6_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K-A Aliev","year":"2020","unstructured":"Aliev, K.-A., Sevastopolsky, A., Kolos, M., Ulyanov, D., Lempitsky, V.: Neural point-based graphics. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 696\u2013712. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58542-6_42"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Anciukevicius, T., Xu, Z., Fisher, M., Henderson, P., Bilen, H., Mitra, N.J., Guerrero, P.: RenderDiffusion: image diffusion for 3D reconstruction, inpainting and generation. arXiv.cs abs\/2211.09869 (2022)","DOI":"10.1109\/CVPR52729.2023.01213"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Tancik, M., Hedman, P., Martin-Brualla, R., Srinivasan, P.P.: 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 (2021)","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"25_CR4","unstructured":"Bhat, S.F., Birkl, R., Wofk, D., Wonka, P., M\u00fcller, M.: ZoeDepth: zero-shot transfer by combining relative and metric depth. arXiv preprint arXiv:2302.12288 (2023)"},{"key":"25_CR5","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying MMD GANs. arXiv preprint arXiv:1801.01401 (2018)"},{"key":"25_CR6","unstructured":"Birkl, R., Wofk, D., M\u00fcller, M.: Midas v3. 1\u2013a model zoo for robust monocular relative depth estimation. arXiv preprint arXiv:2307.14460 (2023)"},{"key":"25_CR7","unstructured":"Bond-Taylor, S., Willcocks, C.G.: Gradient origin networks. arXiv preprint arXiv:2007.02798 (2020)"},{"key":"25_CR8","unstructured":"Cao, A., Johnson, J., Vedaldi, A., Novotny, D.: Lightplane: highly-scalable components for neural 3D fields. arXiv preprint arXiv:2404.19760 (2024)"},{"key":"25_CR9","unstructured":"Cao, Z., Hong, F., Wu, T., Pan, L., Liu, Z.: Large-vocabulary 3D diffusion model with transformer. arXiv preprint arXiv:2309.07920 (2023)"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et\u00a0al.: Efficient geometry-aware 3D generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16123\u201316133 (2022)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Chan, E.R., Monteiro, M., Kellnhofer, P., Wu, J., Wetzstein, G.: pi-GAN: periodic implicit generative adversarial networks for 3d-aware image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5799\u20135809 (2021)","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et al.: GeNVS: generative novel view synthesis with 3D-aware diffusion models. In: arXiv (2023)","DOI":"10.1109\/ICCV51070.2023.00389"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Chen, A., Xu, Z., Geiger, A., Yu, J., Su, H.: TensoRF: tensorial radiance fields. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Chen, A., et al.: MVSNeRF: fast generalizable radiance field reconstruction from multi-view stereo. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14124\u201314133 (2021)","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Gadelha, M., Maji, S., Wang, R.: 3D shape induction from 2D views of multiple objects. In: arXiv (2016)","DOI":"10.1109\/3DV.2017.00053"},{"key":"25_CR16","unstructured":"Gao, J., et al.: Get3D: a generative model of high quality 3D textured shapes learned from images. In: Advances In Neural Information Processing Systems (2022)"},{"key":"25_CR17","unstructured":"Gao, K., Gao, Y., He, H., Lu, D., Xu, L., Li, J.: NeRF: neural radiance field in 3D vision, a comprehensive review. arXiv preprint arXiv:2210.00379 (2022)"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Garbin, S.J., Kowalski, M., Johnson, M., Shotton, J., Valentin, J.P.C.: FastNeRF: high-fidelity neural rendering at 200FPS. In: arXiv. vol. abs\/2103.10380 (2021)","DOI":"10.1109\/ICCV48922.2021.01408"},{"key":"25_CR19","unstructured":"Gu, J., Liu, L., Wang, P., Theobalt, C.: StyleNeRF: a style-based 3D-aware generator for high-resolution image synthesis. arXiv preprint arXiv:2110.08985 (2021)"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Gu, X., Fan, Z., Zhu, S., Dai, Z., Tan, F., Tan, P.: Cascade cost volume for high-resolution multi-view stereo and stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2495\u20132504 (2020)","DOI":"10.1109\/CVPR42600.2020.00257"},{"key":"25_CR21","unstructured":"Gupta, A., Xiong, W., Nie, Y., Jones, I., O\u011fuz, B.: 3DGEN: triplane latent diffusion for textured mesh generation. arXiv preprint arXiv:2303.05371 (2023)"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Henzler, P., Mitra, N.J., Ritschel, T.: Escaping plato\u2019s cave using adversarial training: 3D shape from unstructured 2D image collections. In: Proceedings of the ICCV (2019)","DOI":"10.1109\/ICCV.2019.01008"},{"key":"25_CR24","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local NASH equilibrium. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"25_CR25","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models (2020)"},{"key":"25_CR26","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"25_CR27","unstructured":"Hong, Y., et al.: LRM: large reconstruction model for single image to 3D. arXiv preprint arXiv:2311.04400 (2023)"},{"key":"25_CR28","unstructured":"Kar, A., H\u00e4ne, C., Malik, J.: Learning a multi-view stereo machine. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Kar, A., Tulsiani, S., Carreira, J., Malik, J.: Category-specific object reconstruction from a single image. In: Proceedings of the CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298807"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Karnewar, A., Mitra, N.J., Vedaldi, A., Novotny, D.: HoloFusion: towards photo-realistic 3D generative modeling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22976\u201322985 (2023)","DOI":"10.1109\/ICCV51070.2023.02100"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Karnewar, A., Ritschel, T., Wang, O., Mitra, N.: ReLU Fields: the little non-linearity that could. In: ACM SIGGRAPH 2022 Conference Proceedings, pp.\u00a01\u20139 (2022)","DOI":"10.1145\/3528233.3530707"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Karnewar, A., Vedaldi, A., Novotny, D., Mitra, N.: HoloDiffusion: training a 3D diffusion model using 2D images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01767"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Karnewar, A., Wang, O., Ritschel, T., Mitra, N.: 3inGAN: learning a 3D generative model from images of a self-similar scene. arXiv preprint arXiv:2211.14902 (2022)","DOI":"10.1109\/3DV57658.2022.00046"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4) (2023). https:\/\/repo-sam.inria.fr\/fungraph\/3d-gaussian-splatting\/","DOI":"10.1145\/3592433"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Li, W., Chen, X., Wang, J., Chen, B.: Patch-based 3D natural scene generation from a single example. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16762\u201316772 (2023)","DOI":"10.1109\/CVPR52729.2023.01608"},{"key":"25_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"25_CR37","first-page":"15651","volume":"33","author":"L Liu","year":"2020","unstructured":"Liu, L., Gu, J., Zaw Lin, K., Chua, T.S., Theobalt, C.: Neural sparse voxel fields. Adv. Neural. Inf. Process. Syst. 33, 15651\u201315663 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR38","unstructured":"Liu, M., et al.: One-2-3-45: Any single image to 3D mesh in 45 seconds without per-shape optimization. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"25_CR39","unstructured":"Liu, Y., et al.: Neural rays for occlusion-aware image-based rendering. arXiv.cs abs\/2107.13421 (2022)"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Lombardi, S., Simon, T., Saragih, J., Schwartz, G., Lehrmann, A., Sheikh, Y.: Neural volumes: learning dynamic renderable volumes from images. arXiv preprint arXiv:1906.07751 (2019)","DOI":"10.1145\/3306346.3323020"},{"key":"25_CR41","doi-asserted-by":"publisher","unstructured":"Long, X., Lin, C., Wang, P., Komura, T., Wang, W.: SparseNeuS: fast generalizable neural surface reconstruction from sparse views. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, vol. 13692, pp. 210\u2013227. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_13","DOI":"10.1007\/978-3-031-19824-3_13"},{"key":"25_CR42","doi-asserted-by":"crossref","unstructured":"Martel, J.N., et al.: ACORN: adaptive coordinate networks for neural scene representation. arXiv preprint arXiv:2105.02788 (2021)","DOI":"10.1145\/3476576.3476607"},{"issue":"2","key":"25_CR43","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/2945.468400","volume":"1","author":"N Max","year":"1995","unstructured":"Max, N.: Optical models for direct volume rendering. IEEE Trans. Visual Comput. Graph. 1(2), 99\u2013108 (1995)","journal-title":"IEEE Trans. Visual Comput. Graph."},{"key":"25_CR44","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. In: Proceedings of the ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"25_CR45","doi-asserted-by":"crossref","unstructured":"M\u00fcller, N., Siddiqui, Y., Porzi, L., Bul\u00f2, S.R., Kontschieder, P., Nie\u00dfner, M.: DiffRF: rendering-guided 3D radiance field diffusion. arXiv preprint arXiv:2212.01206 (2022)","DOI":"10.1109\/CVPR52729.2023.00421"},{"key":"25_CR46","doi-asserted-by":"crossref","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. arXiv preprint arXiv:2201.05989 (2022)","DOI":"10.1145\/3528223.3530127"},{"key":"25_CR47","doi-asserted-by":"crossref","unstructured":"Nguyen, P., Karnewar, A., Huynh, L., Rahtu, E., Matas, J., Heikkila, J.: RGBD-Net: predicting color and depth images for novel views synthesis. In: 2021 International Conference on 3D Vision (3DV), pp. 1095\u20131105. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00117"},{"key":"25_CR48","doi-asserted-by":"crossref","unstructured":"Nguyen-Phuoc, T., Li, C., Theis, L., Richardt, C., Yang, Y.: HoloGAN: unsupervised learning of 3D representations from natural images. arXiv.cs abs\/1904.01326 (2019)","DOI":"10.1109\/ICCV.2019.00768"},{"key":"25_CR49","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Mescheder, L.M., Oechsle, M., Geiger, A.: Occupancy flow: 4D reconstruction by learning particle dynamics. In: Proceedings of the ICCV (2019)","DOI":"10.1109\/ICCV.2019.00548"},{"key":"25_CR50","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"25_CR51","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"25_CR52","doi-asserted-by":"crossref","unstructured":"Rakhimov, R., Ardelean, A.T., Lempitsky, V., Burnaev, E.: NPBG++: accelerating neural point-based graphics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15969\u201315979 (2022)","DOI":"10.1109\/CVPR52688.2022.01550"},{"key":"25_CR53","doi-asserted-by":"crossref","unstructured":"Reizenstein, J., Shapovalov, R., Henzler, P., Sbordone, L., Labatut, P., Novotny, D.: Common Objects in 3D: large-scale learning and evaluation of real-life 3D category reconstruction. In: Proceedings of the CVPR (2021)","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"25_CR54","doi-asserted-by":"crossref","unstructured":"Resindra\u00a0Widya, A., Torii, A., Okutomi, M.: Structure-from-motion using dense CNN features with keypoint relocalization. arXiv e-prints, pp. arXiv\u20131805 (2018)","DOI":"10.1186\/s41074-018-0042-y"},{"key":"25_CR55","first-page":"20154","volume":"33","author":"K Schwarz","year":"2020","unstructured":"Schwarz, K., Liao, Y., Niemeyer, M., Geiger, A.: GRAF: generative radiance fields for 3d-aware image synthesis. Adv. Neural. Inf. Process. Syst. 33, 20154\u201320166 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR56","unstructured":"Schwarz, K., Sauer, A., Niemeyer, M., Liao, Y., Geiger, A.: VoxGRAF: fast 3D-aware image synthesis with sparse voxel grids. ARXIV (2022)"},{"key":"25_CR57","first-page":"6087","volume":"34","author":"T Shen","year":"2021","unstructured":"Shen, T., Gao, J., Yin, K., Liu, M.Y., Fidler, S.: Deep marching tetrahedra: a hybrid representation for high-resolution 3D shape synthesis. Adv. Neural. Inf. Process. Syst. 34, 6087\u20136101 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR58","unstructured":"Shi, Z., Peng, S., Xu, Y., Geiger, A., Liao, Y., Shen, Y.: Deep generative models on 3D representations: a survey. arXiv preprint arXiv:2210.15663 (2022)"},{"key":"25_CR59","unstructured":"Sitzmann, V., Martel, J.N.P., Bergman, A.W., Lindell, D.B., Wetzstein, G.: Implicit neural representations with periodic activation functions. In: Proceedings of the NeurIPS (2020)"},{"key":"25_CR60","unstructured":"Sitzmann, V., Zollh\u00f6fer, M., Wetzstein, G.: Scene representation networks: continuous 3D-structure-aware neural scene representations. In: Proceedings of the NeurIPS (2019)"},{"key":"25_CR61","doi-asserted-by":"crossref","unstructured":"Son, M., Park, J.J., Guibas, L., Wetzstein, G.: SinGRAF: learning a 3D generative radiance field for a single scene. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8507\u20138517 (2023)","DOI":"10.1109\/CVPR52729.2023.00822"},{"key":"25_CR62","doi-asserted-by":"crossref","unstructured":"Sun, C., Sun, M., Chen, H.T.: Direct voxel grid optimization: super-fast convergence for radiance fields reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5459\u20135469 (2022)","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"25_CR63","doi-asserted-by":"crossref","unstructured":"Takikawa, T., et al.: Variable bitrate neural fields. In: ACM SIGGRAPH 2022 Conference Proceedings, pp.\u00a01\u20139 (2022)","DOI":"10.1145\/3528233.3530727"},{"key":"25_CR64","doi-asserted-by":"crossref","unstructured":"Tewari, A., et\u00a0al.: State of the art on neural rendering. In: Computer Graphics Forum, vol.\u00a039, pp. 701\u2013727. Wiley Online Library (2020)","DOI":"10.1111\/cgf.14022"},{"key":"25_CR65","doi-asserted-by":"crossref","unstructured":"Tewari, A., et\u00a0al.: Advances in neural rendering. In: Computer Graphics Forum, vol.\u00a041, pp. 703\u2013735. Wiley Online Library (2022)","DOI":"10.1111\/cgf.14507"},{"key":"25_CR66","unstructured":"Tewari, A., et al.: Diffusion with forward models: solving stochastic inverse problems without direct supervision. arXiv preprint arXiv:2306.11719 (2023)"},{"key":"25_CR67","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"25_CR68","doi-asserted-by":"crossref","unstructured":"Wang, P., et al.: F2-NeRF: fast neural radiance field training with free camera trajectories. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4150\u20134159 (2023)","DOI":"10.1109\/CVPR52729.2023.00404"},{"key":"25_CR69","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: IBRNet: learning multi-view image-based rendering. In: Proceedings of the CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"25_CR70","doi-asserted-by":"crossref","unstructured":"Wang, T., et\u00a0al.: Rodin: a generative model for sculpting 3D digital avatars using diffusion. arXiv preprint arXiv:2212.06135 (2022)","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"25_CR71","unstructured":"Wang, Z., Simoncelli, E.P., Bovik, A.C.: Multiscale structural similarity for image quality assessment. In: The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003, vol.\u00a02, pp. 1398\u20131402. IEEE (2003)"},{"key":"25_CR72","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1007\/978-3-030-58452-8_14","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Wei","year":"2020","unstructured":"Wei, X., Zhang, Y., Li, Z., Fu, Y., Xue, X.: DeepSFM: structure from motion via deep bundle adjustment. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 230\u2013247. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_14"},{"key":"25_CR73","first-page":"4058","volume":"46","author":"X Wei","year":"2023","unstructured":"Wei, X., Zhang, Y., Ren, X., Li, Z., Fu, Y., Xue, X.: DeepSFM: robust deep iterative refinement for structure from motion. IEEE Trans. Pattern Anal. Mach. Intell. 46, 4058\u20134074 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR74","doi-asserted-by":"crossref","unstructured":"Wiles, O., Gkioxari, G., Szeliski, R., Johnson, J.: SynSin: end-to-end view synthesis from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7467\u20137477 (2020)","DOI":"10.1109\/CVPR42600.2020.00749"},{"key":"25_CR75","unstructured":"Wu, J., Zhang, C., Xue, T., Freeman, B., Tenenbaum, J.: Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"25_CR76","unstructured":"Wu, R., Liu, R., Vondrick, C., Zheng, C.: Sin3DM: learning a diffusion model from a single 3D textured shape. arXiv preprint arXiv:2305.15399 (2023)"},{"key":"25_CR77","doi-asserted-by":"crossref","unstructured":"Wu, R., Zheng, C.: Learning to generate 3D shapes from a single example. arXiv preprint arXiv:2208.02946 (2022)","DOI":"10.1145\/3550454.3555480"},{"key":"25_CR78","unstructured":"Wu, T., et\u00a0al.: OmniObject3D github code and dataset (2023). https:\/\/github.com\/omniobject3d\/OmniObject3D"},{"key":"25_CR79","doi-asserted-by":"crossref","unstructured":"Wu, T., et\u00a0al.: OmniObject3D: large-vocabulary 3D object dataset for realistic perception, reconstruction and generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 803\u2013814 (2023)","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"25_CR80","doi-asserted-by":"crossref","unstructured":"Xie, Y., et al.: Neural fields in visual computing and beyond. In: Computer Graphics Forum, vol.\u00a041, pp. 641\u2013676. Wiley Online Library (2022)","DOI":"10.1111\/cgf.14505"},{"key":"25_CR81","doi-asserted-by":"crossref","unstructured":"Yang, J., Luo, K.Z., Li, J., Weinberger, K.Q., Tian, Y., Wang, Y.: Denoising vision transformers. arXiv preprint arXiv:2401.02957 (2024)","DOI":"10.1007\/978-3-031-73013-9_26"},{"key":"25_CR82","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. arXiv preprint arXiv:2401.10891 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"25_CR83","doi-asserted-by":"crossref","unstructured":"Yu, A., Fridovich-Keil, S., Tancik, M., Chen, Q., Recht, B., Kanazawa, A.: Plenoxels: radiance fields without neural networks. arXiv preprint arXiv:2112.05131 (2021)","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"25_CR84","doi-asserted-by":"crossref","unstructured":"Yu, A., Li, R., Tancik, M., Li, H., Ng, R., Kanazawa, A.: PlenOctrees for real-time rendering of neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5752\u20135761 (2021)","DOI":"10.1109\/ICCV48922.2021.00570"},{"key":"25_CR85","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., Kanazawa, A.: PixelNeRF: neural radiance fields from one or few images. In: Proceedings of the CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"25_CR86","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: 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 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"25_CR87","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wu, S., Snavely, N., Wu, J.: Seeing a rose in five thousand ways. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 962\u2013971 (2023)","DOI":"10.1109\/CVPR52729.2023.00099"},{"key":"25_CR88","doi-asserted-by":"crossref","unstructured":"Zhou, T., Tucker, R., Flynn, J., Fyffe, G., Snavely, N.: Stereo magnification: learning view synthesis using multiplane images. arXiv preprint arXiv:1805.09817 (2018)","DOI":"10.1145\/3197517.3201323"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73223-2_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T23:21:24Z","timestamp":1733008884000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73223-2_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,8]]},"ISBN":["9783031732225","9783031732232"],"references-count":88,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73223-2_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,8]]},"assertion":[{"value":"8 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}