{"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":1779948106939,"version":"3.53.1"},"reference-count":69,"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\/3dv69130.2026.00069","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"659-669","source":"Crossref","is-referenced-by-count":0,"title":["TwoSquared: 4D Generation from 2D Image Pairs"],"prefix":"10.1109","author":[{"given":"Lu","family":"Sang","sequence":"first","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehranaz","family":"Canfes","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongliang","family":"Cao","sequence":"additional","affiliation":[{"name":"University of Bonn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Riccardo","family":"Marin","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"Bernard","sequence":"additional","affiliation":[{"name":"University of Bonn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Cremers","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Virtual Reality","year":"2019"},{"key":"ref2","article-title":"Videophy: Evaluating physical commonsense for video generation","author":"Bansal","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","author":"Bradbury","year":"2018","journal-title":"JAX: composable transformations of Python+NumPy programs"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2969\/aspm\/06710059"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01937"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01083"},{"key":"ref7","article-title":"A physical coherence benchmark for evaluating video generation models via optical flow-guided frame prediction","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00181"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00430"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.56021\/9781421407944"},{"key":"ref13","first-page":"11808","article-title":"Nerfdiff: Single-image view synthesis with nerf-guided distillation from 3d-aware diffusion","volume-title":"International Conference on Machine Learning","author":"Gu","year":"2023"},{"issue":"2","key":"ref14","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref15","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"arXiv preprint","author":"Hu","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74298-2_13"},{"key":"ref17","article-title":"Consistent4d: Consistent 360\u00b0 dynamic object generation from monocular video","volume-title":"The Twelfth International Conference on Learning Representations","author":"Jiang","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0972-7_16"},{"key":"ref20","first-page":"21377","article-title":"Dreammesh4d: Video-to-4d generation with sparse-controlled gaussianmesh hybrid representation","volume":"37","author":"Li","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3519"},{"key":"ref22","article-title":"Phys4dgen: A physics-driven framework for controllable and efficient 4d content generation from a single image","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"One-2\u20133-45: Any single image to 3 d mesh in 45 seconds without per-shape optimization","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00853"},{"key":"ref25","article-title":"Syncdreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref27","article-title":"Clay: A controllable large-scale generative model for creating high-quality 3d assets","author":"Longwen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00061"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00816"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_3"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185526"},{"key":"ref33","article-title":"Echo: Ego-centric modeling of human-object interactions","author":"Petrov","year":"2025","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00524"},{"key":"ref35","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref36","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"ref38","article-title":"Magic123: One image to high-quality 3d object generation using both 2d and 3d diffusion priors","author":"Qian","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","article-title":"Implicit neural surface deformation with explicit velocity fields","author":"Sang","year":"2025","journal-title":"ICLR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00613"},{"key":"ref42","volume-title":"Augmented Reality: Principles and Practice","author":"Schmalstieg","year":"2016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_19"},{"key":"ref44","article-title":"Anything3d: Towards single-view anything reconstruction in the wild","author":"Shen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","first-page":"109","article-title":"As-rigid-as-possible surface modeling","volume-title":"Symposium on Geometry processing","author":"Sorkine","year":"2007"},{"key":"ref47","article-title":"Dimensionx: Create any 3d and 4d scenes from a single image with controllable video diffusion","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"ref50","article-title":"Tencent Hunyuan3D Team","year":"2025","journal-title":"Hunyuan3d 2.0: Scaling diffusion models for high resolution textured 3d assets generation"},{"key":"ref51","author":"Vu","year":"2024","journal-title":"Rfnet-4d++: Joint object reconstruction and flow estimation from 4d point clouds with cross-attention spatio-temporal features"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00059"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00876"},{"key":"ref55","article-title":"Unique3d: High-quality and efficient 3d mesh generation from a single image","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00435"},{"key":"ref57","article-title":"Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Human 3diffusion: Realistic avatar creation via explicit 3d consistent diffusion models","author":"Xue","year":"2024","journal-title":"Arxiv"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3577067"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00801"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3592442"},{"key":"ref62","article-title":"4diffusion: Multi-view video diffusion model for 4 d generation","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0488"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00756"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00948"},{"key":"ref66","article-title":"Michelangelo: Conditional 3d shape generation based on shape-image-text aligned latent representation","volume":"36","author":"Zhao","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref67","article-title":"Ar4d: Autoregressive 4d generation from monocular videos","author":"Zhu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00983"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00514"}],"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\/11533272.pdf?arnumber=11533272","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:02:21Z","timestamp":1779944541000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533272\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00069","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}