{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T23:12:27Z","timestamp":1780528347680,"version":"3.54.1"},"reference-count":87,"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":"NSFC","doi-asserted-by":"publisher","award":["62172348"],"award-info":[{"award-number":["62172348"]}],"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\/iccv51701.2025.02323","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"01-12","source":"Crossref","is-referenced-by-count":2,"title":["Hi3dgen: High-Fidelity 3D Geometry Generation From Images Via Normal Bridging"],"prefix":"10.1109","author":[{"given":"Chongjie","family":"Ye","sequence":"first","affiliation":[{"name":"FNii-Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yushuang","family":"Wu","sequence":"additional","affiliation":[{"name":"ByteDance Games"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziteng","family":"Lu","sequence":"additional","affiliation":[{"name":"SSE, CUHKSZ"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahao","family":"Chang","sequence":"additional","affiliation":[{"name":"SSE, CUHKSZ"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyang","family":"Guo","sequence":"additional","affiliation":[{"name":"ByteDance Games"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqing","family":"Zhou","sequence":"additional","affiliation":[{"name":"ByteDance Games"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Zhao","sequence":"additional","affiliation":[{"name":"AIR, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoguang","family":"Han","sequence":"additional","affiliation":[{"name":"SSE, CUHKSZ"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00911"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01289"},{"key":"ref3","first-page":"3","article-title":"Edify 3d: Scalable high-quality 3d asset generation","author":"Bala","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","first-page":"1","article-title":"Depth pro: Sharp monocular metric depth in less than a second","volume":"6","author":"Bochkovskii","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00500"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01945"},{"key":"ref7","first-page":"16123","article-title":"Efficient geometry-aware 3d generative adversarial networks","author":"Eric","year":"2022","journal-title":"CVPR"},{"key":"ref8","first-page":"2","article-title":"Shapenet: An information-rich 3d model repository","author":"Angel","year":"2015","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00616"},{"key":"ref10","first-page":"2","article-title":"Dora: Sampling and benchmarking for 3d shape variational auto-encoders","volume":"6","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02045"},{"key":"ref12","volume-title":"Rodin gen-1: A production-level 3d generation model","author":"Deemos","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref14","first-page":"2, 5, 6","article-title":"Objaverse-xl: A universe of 10 ~\\mathrm{m}+3 ~\\mathrm{d} objects","volume":"36","author":"Deitke","year":"2024","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01370"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00398"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01534-z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref22","volume-title":"Github: Where the world builds software","year":"2025"},{"key":"ref23","first-page":"8016580190","article-title":"Tetrahedron splatting for 3d generation","volume":"37","author":"Gu","year":"2025","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2023.3340617"},{"key":"ref25","first-page":"6","article-title":"Lotus: Diffusion-based visual foundation model for high-quality dense prediction","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","first-page":"1","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2021","journal-title":"NeurIPSW"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073232"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-0031-y"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00437"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01268"},{"key":"ref31","first-page":"76061","article-title":"Navi: Category-agnostic image collections with high-quality 3d shape and pose annotations","volume":"36","author":"Jampani","year":"2023","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01550"},{"key":"ref35","volume-title":"Flux. 1 dev: Open-weight text-to-image generation model","year":"2025"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417861"},{"issue":"3","key":"ref37","first-page":"5, 6","article-title":"Craftsman: High-fidelity mesh generation with 3d native generation and interactive geometry refiner","volume":"1","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3633512"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859655"},{"key":"ref40","first-page":"3","article-title":"Meshformer: High-quality mesh generation with 3d-guided reconstruction model","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","first-page":"1","volume":"6","author":"Logothetis","year":"2024","journal-title":"Luces-mv: A multi-view dataset for nearfield point light source photometric stereo"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref43","first-page":"1","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00835"},{"key":"ref45","first-page":"1","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research Journal"},{"key":"ref46","first-page":"3","article-title":"Envision3d: One image to 3d with anchor views interpolation","author":"Pang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref48","first-page":"3","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00946"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref54","first-page":"1","volume-title":"Dora: Sampling and benchmarking for 3d shape variational auto-encoders","volume":"8","author":"Chen","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"ref56","first-page":"6","article-title":"Meta 3d assetgen: Text-to-mesh generation with highquality geometry, texture, and pbr materials","author":"Siddiqui","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","author":"Smith","year":"2025","journal-title":"Thingiverse"},{"key":"ref58","first-page":"3","article-title":"Dreamcraft3d++: Efficient hierarchical 3d generation with multi-plane reconstruction model","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Tencent Hunyuan3D Team","volume-title":"Hunyuan3d 2.0: High-resolution 3d asset generation","year":"2025"},{"issue":"6","key":"ref60","first-page":"2","article-title":"Llama 2: Open foundation and fine-tuned chat models","volume":"5","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","first-page":"6","article-title":"Tripo AI","volume-title":"Tripo ai - create your first 3d model with text","year":"2025"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00167"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_9"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00077"},{"key":"ref66","first-page":"3","article-title":"Orient anything: Learning robust object orientation estimation from rendering 3d models","volume":"6","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","first-page":"893","article-title":"Diffusiondb: A large-scale prompt gallery dataset for text-toimage generative models","author":"Zijie","year":"2023","journal-title":"ACL"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2432"},{"key":"ref69","first-page":"3","article-title":"Unique3d: High-quality and efficient 3d mesh generation from a single image","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","first-page":"3, 5","article-title":"Direct3d: Scalable image-to-3d generation via 3d latent diffusion transformer","volume":"1","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3687973"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298801"},{"issue":"5","key":"ref74","first-page":"6, 7, 1","article-title":"Structured 3d latents for scalable and versatile 3d generation","volume":"3","author":"Xiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01294"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00057"},{"issue":"6","key":"ref77","first-page":"1","article-title":"What matters when repurposing diffusion models for general dense perception tasks?","volume":"2","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref78","first-page":"3","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":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02479"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3687971"},{"key":"ref81","first-page":"91509161","article-title":"Mvimgnet: A largescale dataset of multi-view images","author":"Yu","year":"2023","journal-title":"CVPR"},{"key":"ref82","first-page":"25018","article-title":"Monosdf: Exploring monocular geometric cues for neural implicit surface reconstruction","volume":"35","author":"Yu","year":"2022","journal-title":"NeurIPS"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00423"},{"key":"ref86","first-page":"6","article-title":"Hunyuan3d 2.0: Scaling diffusion models for high resolution textured 3d assets generation","author":"Zhao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657403"}],"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\/11444123.pdf?arnumber=11444123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:45:46Z","timestamp":1777531546000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444123\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02323","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}