{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:01:42Z","timestamp":1779948102806,"version":"3.53.1"},"reference-count":98,"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\/3dv69130.2026.00130","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"1-31","source":"Crossref","is-referenced-by-count":0,"title":["DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flow"],"prefix":"10.1109","author":[{"given":"Ken","family":"Deng","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan-Chen","family":"Guo","sequence":"additional","affiliation":[{"name":"VAST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingxiang","family":"Sun","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zi-Xin","family":"Zou","sequence":"additional","affiliation":[{"name":"VAST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangguang","family":"Li","sequence":"additional","affiliation":[{"name":"VAST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Cai","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan-Pei","family":"Cao","sequence":"additional","affiliation":[{"name":"VAST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yebin","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ding","family":"Liang","sequence":"additional","affiliation":[{"name":"VAST"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2001269.2001293"},{"issue":"3","key":"ref2","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0391"},{"key":"ref4","author":"Chang","year":"2015","journal-title":"Shapenet: An information-rich 3d model repository"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3494046"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618201"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00162"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01548"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01263"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref14","author":"Johannes","year":"2023","journal-title":"Boosting latent diffusion with flow matching"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_19"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417816"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.161"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408933"},{"key":"ref19","volume-title":"Instant neural surface reconstruction","author":"Guo","year":"2022"},{"key":"ref20","author":"Gupta","year":"2023","journal-title":"3dgen: Triplane latent diffusion for textured mesh generation"},{"key":"ref21","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":"Advances in neural information processing systems"},{"key":"ref22","author":"Ho","year":"2020","journal-title":"Denoising diffusion probabilistic models"},{"key":"ref23","author":"Hong","year":"2024","journal-title":"3dtopia: Large text-to-3d generation model with hybrid diffusion priors"},{"key":"ref24","author":"Hong","year":"2024","journal-title":"Lrm: Large reconstruction model for single image to 3d"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657428"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00298"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref28","author":"Jun","year":"2023","journal-title":"Shap-e: Generating conditional 3d implicit functions"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref30","author":"Li","year":"2023","journal-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model"},{"key":"ref31","author":"Li","year":"2023","journal-title":"Sweetdreamer: Aligning geometric priors in 2d diffusion for consistent text-to-3d"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3633512"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00623"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00960"},{"key":"ref36","author":"Liu","year":"2023","journal-title":"One-2\u20133-45: Any single image to 3 d mesh in 45 seconds without pershape optimization"},{"key":"ref37","author":"Liu","year":"2024","journal-title":"Meshformer: High-quality mesh generation with 3d-guided reconstruction model"},{"key":"ref38","author":"Liu","year":"2024","journal-title":"Meshformer: High-quality mesh generation with 3d-guided reconstruction model"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref40","author":"Liu","year":"2022","journal-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow"},{"key":"ref41","author":"Liu","year":"2024","journal-title":"Syncdreamer: Generating multiview-consistent images from a single-view image"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00951"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073226"},{"key":"ref45","author":"Nichol","year":"2022","journal-title":"Point-e: A system for generating 3d point clouds from complex prompts"},{"key":"ref46","author":"Oquab","year":"2024","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00387"},{"key":"ref48","author":"Perez","year":"2017","journal-title":"Film: Visual reasoning with a general conditioning layer"},{"key":"ref49","author":"Poole","year":"2022","journal-title":"Dreamfusion: Text-to-3d using 2d diffusion"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00946"},{"key":"ref51","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00403"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref55","author":"Shi","year":"2023","journal-title":"Zero123++: a single image to consistent multi-view diffusion base model"},{"key":"ref56","author":"Shi","year":"2024","journal-title":"Mvdream: Multi-view diffusion for 3d generation"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02000"},{"key":"ref58","author":"Sun","year":"2023","journal-title":"Dreamcraft3d: Hierarchical 3d generation with bootstrapped diffusion prior"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3598772"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref61","author":"Tang","year":"2023","journal-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1995.466848"},{"key":"ref64","author":"Tochilkin","year":"2024","journal-title":"Triposr: Fast 3d object reconstruction from a single image"},{"key":"ref65","author":"Wang","year":"2023","journal-title":"Imagedream: Image-prompt multi-view diffusion for 3d generation"},{"key":"ref66","author":"Wang","year":"2023","journal-title":"Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction"},{"key":"ref67","author":"Wang","year":"2023","journal-title":"Pf-lrm: Pose-free large reconstruction model for joint pose and shape prediction"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00305"},{"key":"ref69","author":"Wang","year":"2023","journal-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation"},{"key":"ref70","author":"Wang","year":"2024","journal-title":"Crm: Single image to 3d textured mesh with convolutional reconstruction model"},{"key":"ref71","author":"Wei","year":"2024","journal-title":"Meshlrm: Large reconstruction model for highquality mesh"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126358"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995388"},{"key":"ref74","author":"Wu","year":"2024","journal-title":"Direct3d: Scalable image-to-3d generation via 3d latent diffusion transformer"},{"key":"ref75","author":"Wu","year":"2024","journal-title":"Direct3d: Scalable image-to-3d generation via 3d latent diffusion transformer"},{"key":"ref76","article-title":"Gpt4 v (ision) is a human-aligned evaluator for text-to-3d generation","author":"Wu","year":"2024","journal-title":"In CVPR"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02000"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2671458"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02003"},{"key":"ref80","author":"Xu","year":"2024","journal-title":"Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models"},{"key":"ref81","author":"Xu","year":"2023","journal-title":"Dmv3d: Denoising multi-view diffusion using 3d large reconstruction model"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4020-6754-9_7161"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00775"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00649"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02425"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.186"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3687909"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00407"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3592442"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3091"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_16"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref95","author":"Zhao","year":"2023","journal-title":"Michelangelo: Conditional 3d shape generation based on shape-image-text aligned latent representation"},{"key":"ref96","author":"Zhao","year":"2025","journal-title":"Hunyuan3d 2.0: Scaling diffusion models for high resolution textured 3d assets generation"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14602"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00983"}],"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\/11533214.pdf?arnumber=11533214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:01:47Z","timestamp":1779944507000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533214\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":98,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00130","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}