{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:06:09Z","timestamp":1777889169922,"version":"3.51.4"},"reference-count":100,"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\/iccv51701.2025.01458","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15714-15726","source":"Crossref","is-referenced-by-count":1,"title":["Bootstrap3D: Improving Multi-View Diffusion Model with Synthetic Data"],"prefix":"10.1109","author":[{"given":"Zeyi","family":"Sun","sequence":"first","affiliation":[{"name":"Shanghai Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Wu","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhang","family":"Zang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyi","family":"Dong","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanjun","family":"Xiong","sequence":"additional","affiliation":[{"name":"Adobe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0902-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","author":"Anil","year":"2023","journal-title":"Palm 2 technical report"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00566"},{"key":"ref5","author":"Awadalla","year":"2023","journal-title":"Openflamingo: An opensource framework for training large autoregressive visionlanguage models"},{"issue":"3","key":"ref6","article-title":"Improving image generation with better captions","volume-title":"Computer Science","volume":"2","author":"Betker","year":"2023"},{"key":"ref7","article-title":"BlackForestLabs","year":"2024","journal-title":"Flux: Official inference repository for flux. 1 models, 2024"},{"key":"ref8","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref9","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref10","author":"Brown","year":"2020","journal-title":"Language models are few-shot learners"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref12","first-page":"16123","article-title":"Efficient geometry-aware 3d generative adversarial networks","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Eric","year":"2022"},{"key":"ref13","author":"Angel","year":"2015","journal-title":"Shapenet: An information-rich 3d model repository"},{"key":"ref14","author":"Chen","year":"2023","journal-title":"Pixart- a: Fast training of diffusion transformer for photorealistic text-to-image synthesis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3581312"},{"key":"ref19","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2022","journal-title":"J. Mach. Learn. Res."},{"issue":"70","key":"ref20","first-page":"1","article-title":"Scaling instructionfinetuned language models","volume":"25","author":"Won Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2025.3611489"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00110"},{"key":"ref25","author":"Dong","year":"2024","journal-title":"Internlm-xcomposer2: Mastering free-form text-image composition and comprehension in vision-language large model"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref27","article-title":"Florence. Palm-e: An embodied multimodal language model","volume-title":"International Conference on Machine Learning","author":"Driess","year":"2023"},{"key":"ref28","author":"Esser","year":"2024","journal-title":"Scaling rectified flow transformers for high-resolution image synthesis"},{"key":"ref29","volume-title":"Daniel Gatis etc. Rembg","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3149"},{"key":"ref31","volume-title":"Openlrm: Open-source large reconstruction models","author":"He","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"ref33","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilib-rium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref34","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref35","author":"Hoffmann","year":"2022","journal-title":"Training compute-optimal large language models"},{"key":"ref36","author":"Hong","year":"2023","journal-title":"Lrm: Large reconstruction model for single image to 3d"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3155"},{"key":"ref38","article-title":"Dreamtime: An improved optimization strategy for diffusion-guided 3d generation","author":"Huang","year":"2024","journal-title":"ICLR"},{"key":"ref39","volume-title":"Openclip","author":"Ilharco","year":"2021"},{"key":"ref40","author":"Jun","year":"2023","journal-title":"Shap-e: Generating conditional 3d implicit functions"},{"key":"ref41","author":"Kant","year":"2024","journal-title":"Spad: Spatially aware multiview diffusers"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref43","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref45","author":"Kwak","year":"2023","journal-title":"Vivid-1-to-3: Novel view synthesis with video diffusion models"},{"key":"ref46","author":"Li","year":"2024","journal-title":"Playground v2.5: Three insights towards enhancing aesthetic quality in text-to-image generation"},{"key":"ref47","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li","year":"2022"},{"key":"ref48","author":"Li","year":"2023","journal-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models"},{"key":"ref49","author":"Li","year":"2023","journal-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00623"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00037"},{"key":"ref52","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00960"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref55","author":"Liu","year":"2023","journal-title":"Syncdreamer: Generating multiview-consistent images from a single-view image"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00951"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3291"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.35"},{"key":"ref59","article-title":"OpenAI","year":"2023","journal-title":"Gpt-4v(ision) system card"},{"key":"ref60","first-page":"230308774","article-title":"OpenAI","author":"R","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref62","author":"Podell","year":"2023","journal-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis"},{"key":"ref63","author":"Poole","year":"2022","journal-title":"Dreamfusion: Text-to-3d using 2d diffusion"},{"key":"ref64","author":"Qi","year":"2024","journal-title":"Tailor3d: Customized 3d assets editing and generation with dual-side images"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00946"},{"key":"ref66","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":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref68","author":"Salimans","year":"2022","journal-title":"Progressive distillation for fast sampling of diffusion models"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02278"},{"key":"ref71","author":"Shi","year":"2023","journal-title":"Zero123++: a single image to consistent multi-view diffusion base model"},{"key":"ref72","author":"Shi","year":"2023","journal-title":"Mvdream: Multi-view diffusion for 3d generation"},{"key":"ref73","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01237"},{"key":"ref75","author":"Sun","year":"2024","journal-title":"X-prompt: Towards universal in-context image generation in auto-regressive vision language foundation models"},{"key":"ref76","author":"Tang","year":"2023","journal-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation"},{"key":"ref77","author":"Tang","year":"2024","journal-title":"Lgm: Large multiview gaussian model for high-resolution 3d content creation"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_10"},{"key":"ref79","author":"Team","year":"2023","journal-title":"Gemini: a family of highly capable multimodal models"},{"key":"ref80","author":"Tochilkin","year":"2024","journal-title":"Triposr: Fast 3d object reconstruction from a single image"},{"key":"ref81","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"ref84","author":"Wang","year":"2023","journal-title":"Pf-lrm: Pose-free large reconstruction model for joint pose and shape prediction"},{"key":"ref85","article-title":"Prolificdreamer: Highfidelity and diverse text-to-3d generation with variational score distillation","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_4"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref88","author":"Wei","year":"2024","journal-title":"Meshlrm: Large reconstruction model for highquality mesh"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01006"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02098"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref93","author":"Xing","year":"2025","journal-title":"Scalecap: Inference-time scalable image captioning via dual-modality debiasing"},{"key":"ref94","author":"Xu","year":"2024","journal-title":"Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_1"},{"key":"ref96","author":"Yang","year":"2024","journal-title":"Magic-boost: Boost 3d generation with mutli-view conditioned diffusion"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00186"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00949"},{"key":"ref99","author":"Zhang","year":"2023","journal-title":"Internlm-xcomposer: A vision-language large model for advanced text-image comprehension and composition"},{"key":"ref100","article-title":"Hifa: Highfidelity text-to-3d generation with advanced diffusion guidance","volume-title":"The Twelfth International Conference on Learning Representations","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\/11445785.pdf?arnumber=11445785","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:08:19Z","timestamp":1777612099000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445785\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":100,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01458","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}