{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T06:09:35Z","timestamp":1778652575426,"version":"3.51.4"},"reference-count":39,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFF0904303"],"award-info":[{"award-number":["2022YFF0904303"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61932003"],"award-info":[{"award-number":["61932003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012401","name":"Beijing Science and Technology Plan Project","doi-asserted-by":"publisher","award":["Z221100006322003"],"award-info":[{"award-number":["Z221100006322003"]}],"id":[{"id":"10.13039\/501100012401","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\/iccv51701.2025.00727","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7751-7760","source":"Crossref","is-referenced-by-count":0,"title":["GSV3D: Gaussian Splatting-Based Geometric Distillation With Stable Video Diffusion for Single-Image 3D Object Generation"],"prefix":"10.1109","author":[{"given":"Ye","family":"Tao","sequence":"first","affiliation":[{"name":"Beihang University,State Key Laboratory of Virtual Reality Technology and Systems"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Zhang","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yahao","family":"Shi","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Virtual Reality Technology and Systems"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongqing","family":"Zou","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Zhou","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","year":"2020","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Demystifying mmd gans","author":"Bi\u0144kowski","year":"2018","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref5","article-title":"Meshanything: Artist-created mesh generation with autoregressive transformers","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref9","first-page":"31841","article-title":"Get3d: A generative model of high quality 3d textured shapes learned from images","volume":"35","author":"Gao","year":"2022","journal-title":"NeurIPS"},{"key":"ref10","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref11","article-title":"Lrm: Large reconstruction model for single image to 3d","author":"Hong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Shap-e: Generating conditional 3d implicit functions","author":"Jun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Black Forest Labs","volume-title":"Flux","year":"2024"},{"key":"ref15","article-title":"Gaussiananything: Interactive point cloud latent diffusion for 3d generation","author":"Lan","year":"2025","journal-title":"ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01216"},{"key":"ref17","article-title":"Era3d: High-resolution multiview diffusion using efficient row-wise attention","author":"Li","year":"2024","journal-title":"NeurIPS"},{"key":"ref18","article-title":"Craftsman: High-fidelity mesh generation with 3d native generation and interactive geometry refiner","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref20","article-title":"Meshdiffusion: Score-based generative 3d mesh modeling","author":"Liu","year":"2023","journal-title":"ICLR"},{"key":"ref21","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Point-e: A system for generating 3d point clouds from complex prompts","author":"Nichol","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref24","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687699"},{"key":"ref26","first-page":"10684","article-title":"High-resolution image syn-thesis with latent diffusion models","volume-title":"CVPR","author":"Rombach","year":"2022"},{"key":"ref27","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref28","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","first-page":"1","article-title":"Lgm: Large multi-view gaussian model for high-resolution 3d content creation","volume-title":"ECCV","author":"Tang","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref33","article-title":"Imagedream: Image-prompt multi-view diffusion for 3d generation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","volume":"36","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref35","first-page":"1","article-title":"Grm: Large gaussian reconstruction model for efficient 3d reconstruction and generation","volume-title":"ECCV","author":"Xu","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681634"},{"key":"ref37","article-title":"Lion: Latent point diffusion models for 3d shape generation","author":"Zeng","year":"2022","journal-title":"NeurIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00983"}],"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\/11443550.pdf?arnumber=11443550","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T05:22:53Z","timestamp":1778649773000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443550\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00727","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}