{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:01:57Z","timestamp":1779948117345,"version":"3.53.1"},"reference-count":106,"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\/3dv69130.2026.00126","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"1281-1292","source":"Crossref","is-referenced-by-count":0,"title":["VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space"],"prefix":"10.1109","author":[{"given":"Lin","family":"Li","sequence":"first","affiliation":[{"name":"Beihang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehuan","family":"Huang","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Feng","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gengxiong","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Chen","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunchao","family":"Guo","sequence":"additional","affiliation":[{"name":"Tencent Hunyuan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Sheng","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Bar-On","year":"2025","journal-title":"Editp23: 3d editing via propagation of image prompts to multi-view"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01517"},{"key":"ref3","year":"2025","journal-title":"FLUX. 1 Tools: Introducing Fill, Depth, Canny, and Redux"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3150"},{"key":"ref5","author":"Chen","year":"2024","journal-title":"Generic 3d diffusion adapter using controlled multi-view editing"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02498"},{"key":"ref7","article-title":"Autopartgen: Autogressive 3d part generation and discovery","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3080"},{"key":"ref9","author":"Chen","year":"2024","journal-title":"Meshanything: Artistcreated mesh generation with autoregressive transformers"},{"key":"ref10","author":"Chen","year":"2025","journal-title":"Ultra3d: Efficient and highfidelity 3d generation with part attention"},{"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\/CVPR52734.2025.02650"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00478"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00771"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00771"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00683"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00068"},{"key":"ref21","volume-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.264"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i5.37394"},{"key":"ref24","author":"Gal","year":"2022","journal-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00066"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.00672"},{"key":"ref27","author":"Hao","year":"2024","journal-title":"Meshtron: High-fidelity, artist-like 3d mesh generation at scale"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02469"},{"key":"ref29","author":"Heusel","year":"2018","journal-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium"},{"key":"ref30","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref32","article-title":"Lrm: Large reconstruction model for single image to 3d","author":"Hong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755151"},{"key":"ref34","article-title":"Mv-adapter: Multi-view consistent image generation made easy","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00934"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02202"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref39","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref40","volume-title":"Flux","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01506"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730722"},{"key":"ref43","article-title":"Craftsman: High-fidelity mesh generation with 3d native generation and interactive geometry refiner","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00500"},{"key":"ref45","author":"Li","year":"2025","journal-title":"Step1x3d: Towards high-fidelity and controllable generation of textured 3d assets"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3633512"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3633512"},{"key":"ref48","article-title":"Sparc3d: Sparse representation and construction for high-resolution 3d shapes modeling","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref49","author":"Lin","year":"2025","journal-title":"Partcrafter: Structured 3d mesh generation via compositional latent diffusion transformers"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657482"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72907-2_23"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"ref53","article-title":"One-2\u20133-45: Any single image to 3 d mesh in 45 seconds without per-shape optimization","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref54","article-title":"Syncdreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00069"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref60","author":"Oquab","year":"2024","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref62","author":"Poole","year":"2022","journal-title":"Dreamfusion: Text-to-3d using 2d diffusion"},{"key":"ref63","author":"Qi","year":"2024","journal-title":"Tailor3d: Customized 3d assets editing and generation with dual-side images"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i11.37820"},{"key":"ref65","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"issue":"2","key":"ref66","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687699"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref69","article-title":"Semantic image inversion and editing using rectified stochastic differential equations","author":"Rout","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00046"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.01777"},{"key":"ref73","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref76","author":"Tang","year":"2025","journal-title":"Efficient part-level 3d object generation via dual volume packing"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref78","article-title":"Taming rectified flow for inversion and editing","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref80","author":"Wang","year":"2024","journal-title":"Llama-mesh: Unifying 3d mesh generation with language models"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_4"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730601"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02015"},{"key":"ref84","article-title":"Unique3d: High-quality and efficient 3d mesh generation from a single image","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref85","author":"Wu","year":"2025","journal-title":"Dipo: Dual-state images controlled articulated object generation powered by diverse data"},{"key":"ref86","article-title":"Direct3d: Scalable image-to-3d generation via 3d latent diffusion transformer","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref87","author":"Wu","year":"2025","journal-title":"Direct3d-s2: Gigascale 3d generation made easy with spatial sparse attention"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00858"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3658188"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"ref91","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":"ref92","author":"Yang","year":"2024","journal-title":"Sampart3d: Segment any part in 3d objects"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3757377.3763872"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3730841"},{"key":"ref95","author":"Ye","year":"2025","journal-title":"Shapellm-omni: A native multimodal 11 m for 3d generation and understanding"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3592442"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/3730840"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02293"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.00988"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/3757377.3763972"},{"key":"ref103","article-title":"Michelangelo: Conditional 3d shape generation based on shape-image-text aligned latent representation","volume":"36","author":"Zhao","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref104","author":"Zheng","year":"2025","journal-title":"Pro3d-editor: A progressive-views perspective for consistent and precise 3d editing"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01542"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1145\/3658205"}],"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\/11533325.pdf?arnumber=11533325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:03:01Z","timestamp":1779944581000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533325\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":106,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00126","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}