{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:14Z","timestamp":1777865294416,"version":"3.51.4"},"reference-count":61,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306261"],"award-info":[{"award-number":["62306261"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00243","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2523-2533","source":"Crossref","is-referenced-by-count":0,"title":["Unleashing Vecset Diffusion Model for Fast Shape Generation"],"prefix":"10.1109","author":[{"given":"Zeqiang","family":"Lai","sequence":"first","affiliation":[{"name":"MMLab, CUHK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunfei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tencent Hunyuan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zibo","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tencent Hunyuan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haolin","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent Hunyuan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuyun","family":"Wang","sequence":"additional","affiliation":[{"name":"MMLab, CUHK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiwen","family":"Shi","sequence":"additional","affiliation":[{"name":"Tencent Hunyuan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianghui","family":"Yang","sequence":"additional","affiliation":[{"name":"Tencent Hunyuan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingxiang","family":"Lin","sequence":"additional","affiliation":[{"name":"Tencent Hunyuan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingwei","family":"Huang","sequence":"additional","affiliation":[{"name":"Tencent Hunyuan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhong","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent Hunyuan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tencent Hunyuan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunchao","family":"Guo","sequence":"additional","affiliation":[{"name":"MMLab, CUHK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"Yue","sequence":"additional","affiliation":[{"name":"MMLab, CUHK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"ref2","article-title":"Token merging: Your vit but faster","author":"Bolya","year":"2022","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01514"},{"key":"ref4","article-title":"Deep compression autoencoder for efficient high-resolution diffusion models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01515"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref7","article-title":"Generative Adversarial Nets","volume-title":"NIPS","author":"Goodfellow","year":"2014"},{"key":"ref8","article-title":"Multistep consistency models","author":"Heek","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Lrm: Large reconstruction model for single image to 3d","author":"Hong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02204"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01571"},{"key":"ref12","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"International Conference on machine learning","author":"Jaegle","year":"2021"},{"key":"ref13","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on machine learning","author":"Li","year":"2023"},{"key":"ref15","article-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00500"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0907"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3633512"},{"key":"ref19","author":"Li","year":"2024","journal-title":"Hunyuan-dit: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding"},{"key":"ref20","article-title":"Geometric gan","author":"Lim","year":"2017","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00853"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/280811.281026"},{"key":"ref23","article-title":"Simplifying, stabilizing and scaling continuous-time consistency models","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref25","article-title":"Knowledge distillation in iterative generative models for improved sampling speed","author":"Luhman","year":"2021","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Latent consistency models: Synthesizing high-resolution images with few-step inference","author":"Luo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"ref29","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00239"},{"key":"ref33","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"ICLR","author":"Salimans","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687625"},{"key":"ref36","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Improved techniques for training consistency models","author":"Song","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Improved techniques for training consistency models","volume-title":"ICLR","author":"Song","year":"2024"},{"key":"ref40","article-title":"Consistency models","volume-title":"ICML","author":"Song","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref42","article-title":"Triposr: Fast 3d object reconstruction from a single image","author":"Tochilkin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2668"},{"key":"ref44","article-title":"Diffusion-gan: Training gans with diffusion","volume-title":"ICLR","author":"Wang","year":"2023"},{"key":"ref45","article-title":"Direct3d: Scalable image-to-3d generation via 3d latent diffusion transformer","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02000"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73668-1_19"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00783"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref50","article-title":"Perflow: Piecewise rectified flow as universal plug-and-play accelerator","author":"Yan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Improved distribution matching distillation for fast image synthesis","author":"Yin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref53","first-page":"111000","article-title":"Motion consistency model: Accelerating video diffusion with disentangled motion-appearance distillation","volume":"37","author":"Zhai","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3592442"},{"key":"ref55","author":"Zhang","year":"2024","journal-title":"Sageattention2: Efficient attention with thorough outlier smoothing and per-thread int4 quantization"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref57","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":"ref58","article-title":"Hunyuan3d 2.0: Scaling diffusion models for high resolution textured 3d assets generation","author":"Zhao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Uni3d: Exploring unified 3d representation at scale","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Score identity distillation: Exponentially fast distillation of pretrained diffusion models for one-step generation","volume-title":"ICML","author":"Zhou","year":"2024"},{"key":"ref61","article-title":"Accelerating video diffusion models via distribution matching","author":"Zhu","year":"2024","journal-title":"arXiv preprint"}],"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\/11444181.pdf?arnumber=11444181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:11:20Z","timestamp":1777529480000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00243","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}