{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:32:18Z","timestamp":1777865538658,"version":"3.51.4"},"reference-count":89,"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\/iccv51701.2025.02444","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"26336-26348","source":"Crossref","is-referenced-by-count":0,"title":["MS3D: High-Quality 3D Generation via Multi-Scale Representation Modeling"],"prefix":"10.1109","author":[{"given":"Guan","family":"Luo","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2001269.2001293"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01565"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3592135"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_20"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref11","article-title":"Dora: Sampling and benchmarking for 3d shape variational auto-encoders","author":"Chen","year":"2024","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237269"},{"key":"ref13","article-title":"Flashattention-2: Faster attention with better parallelism and work partitioning","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Dao"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.161"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01611"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408933"},{"key":"ref21","article-title":"LRM: large reconstruction model for single image to 3d","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Hong"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00926"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01811"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00425"},{"key":"ref25","article-title":"Shap-e: Generating conditional 3d implicit functions","author":"Jun","year":"2023","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00956"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417861"},{"key":"ref29","article-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Li"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15206"},{"key":"ref31","article-title":"Craftsman: High-fidelity mesh generation with 3d native generation and interactive geometry refiner","author":"Li","year":"2024","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref33","article-title":"Neural sparse voxel fields","volume-title":"Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020","author":"Liu","year":"2020"},{"key":"ref34","article-title":"One-2\u20133-45: Any single image to 3 d mesh in 45 seconds without pershape optimization","volume-title":"Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023","author":"Liu"},{"key":"ref35","article-title":"Meshformer: High-quality mesh generation with 3d-guided reconstruction model","author":"Liu","year":"2024","journal-title":"CoRR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref37","article-title":"Syncdreamer: Generating multiview-consistent images from a single-view image","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Liu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459863"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_13"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/37401.37422"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"ref43","article-title":"Mixed precision training","volume-title":"6th International Conference on Learning Representations, ICLR 2018","author":"Micikevicius"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2487228.2487235"},{"key":"ref47","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res., 2024"},{"key":"ref48","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Poole"},{"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","article-title":"SAM 2: Segment anything in images and videos","volume":"abs\/2408.00714","author":"Ravi","year":"2024","journal-title":"CoRR"},{"key":"ref52","article-title":"Octree-gs: Towards consistent real-time rendering with lod-structured 3d gaussians","author":"Ren","year":"2024","journal-title":"CoRR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3099"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref56","first-page":"501","article-title":"Pixelwise view selection for unstructured multi-view stereo","volume-title":"Computer Vision - ECCV 2016\u201314th European Conference","author":"Johannes"},{"key":"ref57","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"CoRR"},{"key":"ref58","article-title":"Mvdream: Multi-view diffusion for 3d generation","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Shi"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141964"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01626"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref63","article-title":"Dreamgaussian: Generative gaussian splatting for effi-cient 3d content creation","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Tang"},{"key":"ref64","article-title":"Triposr: Fast 3d object reconstruction from a single image","author":"Tochilkin","year":"2024","journal-title":"CoRR"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"ref67","article-title":"Imagedream: Imageprompt multi-view diffusion for 3d generation","author":"Wang","year":"2023","journal-title":"CoRR"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275050"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275050"},{"key":"ref70","first-page":"27171","article-title":"Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction","volume-title":"Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Wang"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0368"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_4"},{"key":"ref73","article-title":"Meshlrm: Large reconstruction model for highquality mesh","author":"Wei","year":"2024","journal-title":"CoRR"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3658226"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"ref76","article-title":"Structured 3d latents for scalable and versatile 3d generation","author":"Xiang","year":"2024","journal-title":"CoRR"},{"key":"ref77","article-title":"Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models","author":"Xu","year":"2024","journal-title":"CoRR"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00536"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_1"},{"key":"ref80","article-title":"DMV3D: denoising multiview diffusion using 3d large reconstruction model","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Xu"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00570"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3592442"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref87","article-title":"Michelangelo: Conditional 3d shape generation based on shape-image-text aligned latent representation","volume-title":"Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023","author":"Zhao"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3592103"},{"key":"ref89","first-page":"17723","article-title":"Long-short transformer: Efficient transformers for language and vision","volume-title":"Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021","author":"Zhu"}],"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\/11445791.pdf?arnumber=11445791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:48Z","timestamp":1777531608000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445791\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":89,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02444","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}