{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T13:26:12Z","timestamp":1790774772620,"version":"4.1.0"},"reference-count":74,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T00:00:00Z","timestamp":1740528000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T00:00:00Z","timestamp":1740528000000},"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":[[2025,2,26]]},"DOI":"10.1109\/wacv61041.2025.00392","type":"proceedings-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T17:08:13Z","timestamp":1744132093000},"page":"3985-3995","source":"Crossref","is-referenced-by-count":3,"title":["GANFusion: Feed-Forward Text-to-3D with Diffusion in GAN Space"],"prefix":"10.1109","author":[{"given":"Souhaib","family":"Attaiki","sequence":"first","affiliation":[{"name":"LIX, &#x00C9;cole Polytechnique, IPP Paris"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Guerrero","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duygu","family":"Ceylan","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Niloy J.","family":"Mitra","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maks","family":"Ovsjanikov","sequence":"additional","affiliation":[{"name":"LIX, &#x00C9;cole Polytechnique, IPP Paris"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning representations and generative models for 3d point clouds","volume-title":"ICML","author":"Achlioptas","year":"2018"},{"key":"ref2","author":"Aggarwal","year":"2023","journal-title":"Controlled and conditional text to image generation with diffusion prior"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01213"},{"key":"ref4","article-title":"Gaudi: A neural architect for immersive 3d scene generation","author":"Bautista","year":"2022","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_22"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_33"},{"key":"ref7","article-title":"Dreamavatar: Text-and-shape guided 3d hu-man avatar generation via diffusion models","author":"Cao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"pi-gan: Periodic implicit generative ad-versarial networks for 3d-aware image synthesis","volume-title":"CVPR","author":"Chan","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02033"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01978"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01829"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00215"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01041"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01370"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01315"},{"key":"ref18","article-title":"Get3d: A generative model of high quality 3d textured shapes learned from images","author":"Gao","year":"2022","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591552"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00030"},{"key":"ref21","article-title":"Stylenerf: A style-based 3d aware generator for high-resolution image synthesis","volume-title":"ICLR","author":"Gu","year":"2022"},{"key":"ref22","article-title":"3dgen: Triplane latent diffusion for textured mesh generation","author":"Gupta","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Es-caping plato\u2019s cave: 3d shape from adversarial rendering","volume-title":"Computer Vision (ICCV), 2019 IEEE International Conference on Computer Vision","author":"Henzler","year":"2019"},{"key":"ref24","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho","year":"2021"},{"key":"ref26","article-title":"Eva3d: Compositional 3d human generation from 2d image collections","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Lrm: Large reconstruction model for single image to 3d","volume-title":"ICLR","author":"Hong","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00152"},{"key":"ref29","article-title":"Scalable adaptive computation for iterative generation","author":"Jabri","year":"2023","journal-title":"ICML, ICML\u201923"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.01322","article-title":"Avatarcraft: Transforming text into neural human avatars with parameter-ized shape and pose control","volume-title":"ICCV","author":"Jiang","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02100"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01767"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01463"},{"key":"ref36","article-title":"Dreamhuman: Animatable 3d avatars from text","volume":"abs\/2306.09329","author":"Kolotouros","year":"2023","journal-title":"ArXiv"},{"key":"ref37","author":"Lei","year":"2023","journal-title":"Diffusiongan3d: Boosting text-guided 3d generation and domain adaption by combining 3d gans and diffusion priors"},{"key":"ref38","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li","year":"2022"},{"key":"ref39","volume-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model","author":"Li","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459766"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref42","article-title":"One-2\u20133-45: Any single image to 3d mesh in 45 seconds without per-shape optimization","volume":"36","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref43","article-title":"Syncdreamer: Gener-ating multiview-consistent images from a single-view image","volume-title":"ICLR","author":"Liu","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"issue":"6","key":"ref45","first-page":"248:1","article-title":"SMPL: A skinned multi-person linear model","volume-title":"ACM Trans. Graphics (Proc. SIG-GRAPH Asia)","volume":"34","author":"Loper"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01645"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00650"},{"key":"ref48","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58452-8_24","article-title":"Nerf: Representing scenes as neural radiance fields for view synthe-sis","volume-title":"ECCV","author":"Mildenhall","year":"2020"},{"key":"ref49","article-title":"3D-LDM: Neural implicit 3d shape generation with latent diffusion models","author":"Nam","year":"2022","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00255"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"ref52","author":"Ntavelis","year":"2023","journal-title":"Au-todecoding latent 3d diffusion models"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01251"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01246"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00025"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_31"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.14988"},{"key":"ref58","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","volume":"139","author":"Radford","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref60","article-title":"StyleGAN-T: Unlocking the power of GANs for fast large-scale text-to-image synthesis","volume-title":"ICML","author":"Sauer","year":"2023"},{"key":"ref61","article-title":"Graf: Generative radiance fields for 3d-aware image synthesis","author":"Schwarz","year":"2020","journal-title":"NeurIPS"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"ref63","article-title":"Denoising diffusion implicit models","volume-title":"ICLR","author":"Song","year":"2021"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555506"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"ref67","first-page":"82","article-title":"Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling","author":"Wu","year":"2016","journal-title":"NeurIPS, NIPS\u201916"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00209"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00459"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00852"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00464"},{"key":"ref72","article-title":"Lion: Latent point diffusion models for 3d shape generation","author":"Zeng","year":"2022","journal-title":"NeurIPS"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28540"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01738"}],"event":{"name":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2025,2,26]]},"end":{"date-parts":[[2025,3,6]]}},"container-title":["2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10943266\/10943193\/10943384.pdf?arnumber=10943384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T05:45:53Z","timestamp":1744177553000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10943384\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,26]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/wacv61041.2025.00392","relation":{},"subject":[],"published":{"date-parts":[[2025,2,26]]}}}