{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:01:55Z","timestamp":1779948115577,"version":"3.53.1"},"reference-count":64,"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\/3dv69130.2026.00148","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"1556-1566","source":"Crossref","is-referenced-by-count":0,"title":["PromptVFX: Text-Driven Fields for Open-World 3D Gaussian Animation"],"prefix":"10.1109","author":[{"given":"Mert","family":"Kiray","sequence":"first","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Uhlenbruck","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Busam","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"ref3","article-title":"Vd3d: Taming large video diffusion transformers for 3d camera control","author":"Bahmani","year":"2024","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"ref5","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02029"},{"key":"ref10","article-title":"Blender - a 3D modelling and rendering package","year":"2019","journal-title":"Blender Foundation, Stichting Blender Foundation, Amsterdam"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00057"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"ref16","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"CoRR"},{"key":"ref17","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00076"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657448"},{"key":"ref20","first-page":"125879","article-title":"Animate3d: Animating any 3d model with multi-view video diffusion","volume":"37","author":"Jiang","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","author":"Jung","year":"2023","journal-title":"Deformable 3d gaussian splatting for animatable human avatars"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02034"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0518"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00299"},{"key":"ref27","first-page":"21136","article-title":"Gaussianflow: 4 d reconstruction with dynamic 3 d gaussian particle","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Lin","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_20"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref31","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2277"},{"key":"ref35","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00480"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00042"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_21"},{"key":"ref40","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":"ref41","article-title":"Dreamgaussian4d: Generative 4d gaussian splatting","author":"Ren","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref43","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Deep generative models on 3d representations: A survey","author":"Shi","year":"2022","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"The Eleventh International Conference on Learning Representations","author":"Singer","year":"2023"},{"key":"ref46","article-title":"Text-to-4d dynamic scene generation","author":"Singer","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","author":"Vachha","year":"2024","journal-title":"Instruct-gs2gs: Editing 3d gaussian splats with instructions"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01975"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01428"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00093"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00438"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00420"},{"key":"ref54","article-title":"Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_10"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_34"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00676"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00831"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"ref61","first-page":"45256","article-title":"4real: Towards photorealistic 4d scene generation via video diffusion models","volume":"37","author":"Yu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01781"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_22"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_23"}],"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\/11533357.pdf?arnumber=11533357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:03:23Z","timestamp":1779944603000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533357\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00148","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}