{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:01:46Z","timestamp":1779948106898,"version":"3.53.1"},"reference-count":87,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,20]]},"DOI":"10.1109\/3dv69130.2026.00021","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"145-155","source":"Crossref","is-referenced-by-count":0,"title":["M2SVid: End-to-End Inpainting and Refinement for Monocular-to-Stereo Video Conversion"],"prefix":"10.1109","author":[{"given":"Nina","family":"Shvetsova","sequence":"first","affiliation":[{"name":"Google"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Goutam","family":"Bhat","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prune","family":"Truong","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hilde","family":"Kuehne","sequence":"additional","affiliation":[{"name":"Tuebingen AI Center\/University of Tuebingen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Tombari","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"ArXiv"},{"key":"ref4","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref6","author":"Cherel","year":"2023","journal-title":"Infusion: Internal diffusion for video inpainting"},{"key":"ref7","article-title":"GARF: gaussian activated radiance fields for high fidelity reconstruction and pose estimation","author":"Chng","year":"2022","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00428"},{"key":"ref9","article-title":"Svg: 3d stereoscopic video generation via denoising frame matrix","author":"Dai","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref13","article-title":"Cat3d: Create anything in 3d with multi-view diffusion models","volume-title":"NeurIPS","author":"Gao","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00083"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530755"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00582"},{"key":"ref18","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho","year":"2020"},{"key":"ref19","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"ArXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00193"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00583"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01229"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00982"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_24"},{"key":"ref25","author":"Kalischek","year":"2025","journal-title":"Cubediff: Repurposing diffusion-based image models for panorama generation"},{"key":"ref26","article-title":"Learning a multi-view stereo machine","volume-title":"NeurIPS","author":"Kar","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02282"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3456442"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01257"},{"key":"ref32","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2270375"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296377"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32477"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00569"},{"key":"ref37","article-title":"Image inpainting via tractable steering of diffusion models","author":"Liu","year":"2023","journal-title":"ArXiv"},{"key":"ref38","article-title":"One-2\u20133-45: Any single image to 3 d mesh in 45 seconds without pershape optimization","volume-title":"NeurIPS","author":"Liu","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00084"},{"key":"ref43","article-title":"Osv: One step is enough for high-quality image to video generation","author":"Mao","year":"2024","journal-title":"ArXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00421"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00816"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00629"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00977"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14340"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref53","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"ArXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01255"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref57","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"NeurIPS","author":"Saharia","year":"2022"},{"key":"ref58","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"ArXiv"},{"key":"ref59","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02127"},{"key":"ref62","article-title":"Immersepro: End-to-end stereo video synthesis via implicit disparity learning","author":"Shi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref63","article-title":"Stereocrafter-zero: Zero-shot stereo video generation with noisy restart","author":"Shi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00805"},{"key":"ref65","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00408"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00063"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00063"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01258"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/167"},{"key":"ref72","article-title":"NeRF--: Neural radiance fields without known camera parameters","author":"Wang","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00843"},{"key":"ref74","article-title":"Cat4d: Create anything in 4 d with multi-view video diffusion models","author":"Wu","year":"2024","journal-title":"arxiv\/2411.18613"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02036"},{"key":"ref76","article-title":"Sinerf: Sinusoidal neural radiance fields for joint pose estimation and scene reconstruction","author":"Xia","year":"2022","journal-title":"CoRR"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_51"},{"key":"ref78","article-title":"Depth anything v2","author":"Yang","year":"2024","journal-title":"arXiv"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00570"},{"key":"ref81","article-title":"Sdxs: Real-time onestep latent diffusion models with image conditions","author":"Yin","year":"2024","journal-title":"arxiv"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref85","article-title":"Hipa: Enabling one-step text-to-image diffusion models via high-frequency-promoting adaptation","author":"Zhang","year":"2023","journal-title":"ArXiv"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63416-2_156"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00684"}],"event":{"name":"2026 International Conference on 3D Vision (3DV)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2026,3,20]]},"end":{"date-parts":[[2026,3,23]]}},"container-title":["2026 International Conference on 3D Vision (3DV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11533157\/11533158\/11533244.pdf?arnumber=11533244","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:02:05Z","timestamp":1779944525000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533244\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00021","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}