{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:47:06Z","timestamp":1778082426206,"version":"3.51.4"},"publisher-location":"Cham","reference-count":72,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726903","type":"print"},{"value":"9783031726910","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-3-031-72691-0_23","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T18:06:34Z","timestamp":1730570794000},"page":"409-427","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["4DIFF: 3D-Aware Diffusion Model for\u00a0Third-to-First Viewpoint Translation"],"prefix":"10.1007","author":[{"given":"Feng","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mi","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Dimakis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lorenzo","family":"Torresani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gedas","family":"Bertasius","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kristen","family":"Grauman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"23_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/978-3-319-46454-1_16","volume-title":"Computer Vision \u2013 ECCV 2016","author":"S Ardeshir","year":"2016","unstructured":"Ardeshir, S., Borji, A.: Ego2Top: matching viewers in egocentric and\u00a0top-view videos. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 253\u2013268. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_16"},{"key":"23_CR2","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":"23_CR3","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: Mip-NeRF 360: unbounded anti-aliased neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5470\u20135479 (2022)","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"23_CR4","unstructured":"Birkl, R., Wofk, D., M\u00fcller, M.: Midas v3.1 \u2013 a model zoo for robust monocular relative depth estimation. arXiv preprint arXiv:2307.14460 (2023)"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Cao, A., Rockwell, C., Johnson, J.: FWD: real-time novel view synthesis with forward warping and depth. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15713\u201315724 (2022)","DOI":"10.1109\/CVPR52688.2022.01526"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et al.: 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":"23_CR7","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et al.: Generative novel view synthesis with 3D-aware diffusion models. arXiv preprint arXiv:2304.02602 (2023)","DOI":"10.1109\/ICCV51070.2023.00389"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: Learning from RGB-D data in indoor environments. arXiv preprint arXiv:1709.06158 (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"23_CR9","unstructured":"Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Single-stage diffusion NeRF: a unified approach to 3D generation and reconstruction. arXiv preprint arXiv:2304.06714 (2023)","DOI":"10.1109\/ICCV51070.2023.00229"},{"issue":"1","key":"23_CR11","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/MSP.2017.2765202","volume":"35","author":"A Creswell","year":"2018","unstructured":"Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., Bharath, A.A.: Generative adversarial networks: an overview. IEEE Signal Process. Mag. 35(1), 53\u201365 (2018)","journal-title":"IEEE Signal Process. Mag."},{"key":"23_CR12","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Advances in Neural Information Processing Systems, vol. 34, pp. 8780\u20138794 (2021)"},{"issue":"5","key":"23_CR13","first-page":"2567","volume":"44","author":"K Ding","year":"2020","unstructured":"Ding, K., Ma, K., Wang, S., Simoncelli, E.P.: Image quality assessment: unifying structure and texture similarity. IEEE Trans. Pattern Anal. Mach. Intell. 44(5), 2567\u20132581 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Duan, Y., Guo, X., Zhu, Z.: DiffusionDepth: diffusion denoising approach for monocular depth estimation. arXiv preprint arXiv:2303.05021 (2023)","DOI":"10.1007\/978-3-031-73247-8_25"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Flynn, J., et al.: DeepView: view synthesis with learned gradient descent. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2367\u20132376 (2019)","DOI":"10.1109\/CVPR.2019.00247"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Flynn, J., Neulander, I., Philbin, J., Snavely, N.: DeepStereo: learning to predict new views from the world\u2019s imagery. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5515\u20135524 (2016)","DOI":"10.1109\/CVPR.2016.595"},{"key":"23_CR17","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: The KITTI vision benchmark suite 2(5) (2015). https:\/\/www.cvlibs.net\/datasets\/kitti\/"},{"key":"23_CR18","unstructured":"Grauman, K., et al.: Ego-exo4d: Understanding skilled human activity from first-and third-person perspectives. arXiv preprint arXiv:2311.18259 (2023)"},{"key":"23_CR19","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"issue":"1","key":"23_CR20","first-page":"2249","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. J. Mach. Learn. Res. 23(1), 2249\u20132281 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., Van Der\u00a0Maaten, L., Fei-Fei, L., Zitnick, C.L., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2901\u20132910 (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"23_CR23","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)","DOI":"10.1145\/3592433"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Koh, J.Y., Lee, H., Yang, Y., Baldridge, J., Anderson, P.: Pathdreamer: a world model for indoor navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14738\u201314748 (2021)","DOI":"10.1109\/ICCV48922.2021.01447"},{"key":"23_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1007\/978-3-031-19784-0_12","volume-title":"Computer Vision - ECCV 2022","author":"J Kulh\u00e1nek","year":"2022","unstructured":"Kulh\u00e1nek, J., Derner, E., Sattler, T., Babu\u0161ka, R.: Viewformer: NeRf-free neural rendering from few images using transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13675, pp. 198\u2013216. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19784-0_12"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Kwon, T., Tekin, B., St\u00fchmer, J., Bogo, F., Pollefeys, M.: H2O: two hands manipulating objects for first person interaction recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10138\u201310148 (2021)","DOI":"10.1109\/ICCV48922.2021.00998"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Li, J., Liu, K., Wu, J.: Ego-body pose estimation via ego-head pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17142\u201317151 (2023)","DOI":"10.1109\/CVPR52729.2023.01644"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Liu, G., Tang, H., Latapie, H., Yan, Y.: Exocentric to egocentric image generation via parallel generative adversarial network. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2020, pp. 1843\u20131847. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053957"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Liu, G., Tang, H., Latapie, H.M., Corso, J.J., Yan, Y.: Cross-view exocentric to egocentric video synthesis. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 974\u2013982 (2021)","DOI":"10.1145\/3474085.3475596"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van\u00a0Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: 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 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"23_CR31","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":"23_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1007\/978-3-031-72920-1_23","volume-title":"Computer Vision - ECCV 2024","author":"M Luo","year":"2024","unstructured":"Luo, M., Xue, Z., Dimakis, A., Grauman, K.: Put myself in your shoes: lifting the egocentric perspective from exocentric videos. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15096, pp. 407\u2013425. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72920-1_23"},{"issue":"12","key":"23_CR33","doi-asserted-by":"publisher","first-page":"1210","DOI":"10.1119\/1.10264","volume":"44","author":"J Mathews","year":"1976","unstructured":"Mathews, J.: Coordinate-free rotation formalism. Am. J. Phys. 44(12), 1210\u20131210 (1976)","journal-title":"Am. J. Phys."},{"issue":"1","key":"23_CR34","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., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"issue":"6","key":"23_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3355089.3356528","volume":"38","author":"S Niklaus","year":"2019","unstructured":"Niklaus, S., Mai, L., Yang, J., Liu, F.: 3D ken burns effect from a single image. ACM Trans. Graph. (ToG) 38(6), 1\u201315 (2019)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"23_CR36","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Park, K., et al.: Nerfies: deformable neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5865\u20135874 (2021)","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. arXiv preprint arXiv:2212.09748 (2022)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"23_CR39","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":"23_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1007\/978-3-030-58536-5_22","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Popov","year":"2020","unstructured":"Popov, S., Bauszat, P., Ferrari, V.: CoReNet: coherent 3D scene reconstruction from a single RGB image. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 366\u2013383. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_22"},{"key":"23_CR41","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Corona, E., Pons-Moll, G., Moreno-Noguer, F.: D-NeRF: neural radiance fields for dynamic scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10318\u201310327 (2021)","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"23_CR42","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Regmi, K., Borji, A.: Cross-view image synthesis using conditional GANs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3501\u20133510 (2018)","DOI":"10.1109\/CVPR.2018.00369"},{"key":"23_CR44","unstructured":"Ren, B., Tang, H., Sebe, N.: Cascaded cross MLP-mixer GANs for cross-view image translation. arXiv preprint arXiv:2110.10183 (2021)"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Ren, X., Wang, X.: Look outside the room: synthesizing a consistent long-term 3D scene video from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3563\u20133573 (2022)","DOI":"10.1109\/CVPR52688.2022.00355"},{"key":"23_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1007\/978-3-030-58529-7_37","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Riegler","year":"2020","unstructured":"Riegler, G., Koltun, V.: Free view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 623\u2013640. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_37"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Riegler, G., Koltun, V.: Stable view synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12216\u201312225 (2021)","DOI":"10.1109\/CVPR46437.2021.01204"},{"key":"23_CR48","doi-asserted-by":"crossref","unstructured":"Rockwell, C., Fouhey, D.F., Johnson, J.: Pixelsynth: generating a 3D-consistent experience from a single image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14104\u201314113 (2021)","DOI":"10.1109\/ICCV48922.2021.01384"},{"key":"23_CR49","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"23_CR50","doi-asserted-by":"crossref","unstructured":"Rombach, R., Esser, P., Ommer, B.: Geometry-free view synthesis: transformers and no 3D priors. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14356\u201314366 (2021)","DOI":"10.1109\/ICCV48922.2021.01409"},{"key":"23_CR51","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: Image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"23_CR52","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Advances in Neural Information Processing Systems, vol. 35, pp. 36479\u201336494 (2022)"},{"issue":"4","key":"23_CR53","first-page":"4713","volume":"45","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D.J., Norouzi, M.: Image super-resolution via iterative refinement. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4713\u20134726 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR54","doi-asserted-by":"crossref","unstructured":"Sajjadi, M.S., et al.: Scene representation transformer: geometry-free novel view synthesis through set-latent scene representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6229\u20136238 (2022)","DOI":"10.1109\/CVPR52688.2022.00613"},{"key":"23_CR55","doi-asserted-by":"crossref","unstructured":"Sener, F., et al.: Assembly101: a large-scale multi-view video dataset for understanding procedural activities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21096\u201321106 (2022)","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"23_CR56","doi-asserted-by":"crossref","unstructured":"Sitzmann, V., Thies, J., Heide, F., Nie\u00dfner, M., Wetzstein, G., Zollhofer, M.: Deepvoxels: learning persistent 3d feature embeddings. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2437\u20132446 (2019)","DOI":"10.1109\/CVPR.2019.00254"},{"key":"23_CR57","unstructured":"Sitzmann, V., Zollh\u00f6fer, M., Wetzstein, G.: Scene representation networks: continuous 3D-structure-aware neural scene representations. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"23_CR58","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv:2010.02502 (2020). https:\/\/arxiv.org\/abs\/2010.02502"},{"key":"23_CR59","doi-asserted-by":"publisher","first-page":"127063","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: RoFormer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"key":"23_CR60","doi-asserted-by":"crossref","unstructured":"Szymanowicz, S., Rupprecht, C., Vedaldi, A.: Splatter image: ultra-fast single-view 3D reconstruction. arXiv preprint arXiv:2312.13150 (2023)","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"23_CR61","unstructured":"Varma, M., Wang, P., Chen, X., Chen, T., Venugopalan, S., Wang, Z.: Is attention all that neRF needs? In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=xE-LtsE-xx"},{"key":"23_CR62","doi-asserted-by":"crossref","unstructured":"Tang, H., Xu, D., Sebe, N., Wang, Y., Corso, J.J., Yan, Y.: Multi-channel attention selection GAN with cascaded semantic guidance for cross-view image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2417\u20132426 (2019)","DOI":"10.1109\/CVPR.2019.00252"},{"key":"23_CR63","doi-asserted-by":"crossref","unstructured":"Trevithick, A., Yang, B.: GRF: Learning a general radiance field for 3D scene representation and rendering (2020)","DOI":"10.1109\/ICCV48922.2021.01490"},{"key":"23_CR64","doi-asserted-by":"crossref","unstructured":"Tucker, R., Snavely, N.: Single-view view synthesis with multiplane images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 551\u2013560 (2020)","DOI":"10.1109\/CVPR42600.2020.00063"},{"key":"23_CR65","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: IBRNet: learning multi-view image-based rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2021)","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"23_CR66","unstructured":"Watson, D., Chan, W., Martin-Brualla, R., Ho, J., Tagliasacchi, A., Norouzi, M.: Novel view synthesis with diffusion models. arXiv preprint arXiv:2210.04628 (2022)"},{"key":"23_CR67","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":"23_CR68","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":"23_CR69","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 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4578\u20134587 (2021)","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"23_CR70","doi-asserted-by":"crossref","unstructured":"Zhai, M., Bessinger, Z., Workman, S., Jacobs, N.: Predicting ground-level scene layout from aerial imagery. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 867\u2013875 (2017)","DOI":"10.1109\/CVPR.2017.440"},{"key":"23_CR71","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":"23_CR72","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\/978-3-031-72691-0_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T18:10:10Z","timestamp":1730571010000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72691-0_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031726903","9783031726910"],"references-count":72,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72691-0_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 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"}}]}}