{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:58:01Z","timestamp":1777888681866,"version":"3.51.4"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01739","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18714-18724","source":"Crossref","is-referenced-by-count":0,"title":["FlexGen: Flexible Multi-View Generation from Text and Image Inputs"],"prefix":"10.1109","author":[{"given":"Xinli","family":"Xu","sequence":"first","affiliation":[{"name":"HKUST(GZ)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhang","family":"Ge","sequence":"additional","affiliation":[{"name":"HKUST(GZ)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiantao","family":"Lin","sequence":"additional","affiliation":[{"name":"HKUST(GZ)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Feng","sequence":"additional","affiliation":[{"name":"HKUST(GZ)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lie","family":"Xu","sequence":"additional","affiliation":[{"name":"Quwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanfeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Quwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shunsi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Quwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying-Cong","family":"Chen","sequence":"additional","affiliation":[{"name":"HKUST(GZ)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657525"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00314"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612405"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657425"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref10","article-title":"Cat3d: Create anything in 3d with multi-view diffusion models","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00392"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1201\/9781315267845"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.4324\/9780240814315"},{"key":"ref14","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeuIPS)"},{"key":"ref15","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeuIPS)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/37401.37407"},{"key":"ref18","article-title":"Game engines","author":"Lewis","year":"2002","journal-title":"Communications of the ACM"},{"key":"ref19","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning. PMLR, 2023. 2","author":"Li"},{"key":"ref20","volume-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model","author":"Li","year":"2023"},{"key":"ref21","article-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Era3d: High-resolution multiview diffusion using efficient row-wise attention","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00623"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"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":"Scalable 3d captioning with pretrained models","author":"Luo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Im-3d: Iterative multiview diffusion and reconstruction for high-quality 3d generation","author":"Melas-Kyriazi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00735"},{"key":"ref30","article-title":"Computer animation: algorithms and techniques","author":"Parent","year":"2012","journal-title":"Newnes"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref32","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning. PMLR","author":"Radford","year":"2021"},{"key":"ref34","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NeuIPS)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1089\/109493101300117884"},{"key":"ref36","article-title":"Sg-adapter: Enhancing text-to-image generation with scene graph guidance","author":"Shen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Toss: High-quality text-guided novel view synthesis from a single image","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Denoising diffusion implicit models","author":"Song","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","journal-title":"arXiv preprint"},{"key":"ref42","first-page":"1","article-title":"Lgm: Large multi-view gaussian model for high-resolution 3d content creation","volume-title":"European Conference on Computer Vision","author":"Tang","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00541"},{"key":"ref44","article-title":"Imagedream: Image-prompt multi-view diffusion for 3d generation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction","author":"Wang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems (NeuIPS)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_9"},{"key":"ref48","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":"ref49","first-page":"1","article-title":"Grm: Large gaussian reconstruction model for efficient 3d reconstruction and generation","volume-title":"European Conference on Computer Vision","author":"Xu","year":"2024"},{"key":"ref50","article-title":"Volume rendering of neural implicit surfaces","author":"Yariv","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"ref52","article-title":"Reference-only control","volume-title":"Referenceonly control","author":"Zhang","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444894.pdf?arnumber=11444894","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:54:23Z","timestamp":1777611263000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444894\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01739","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}