{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T21:54:47Z","timestamp":1779227687876,"version":"3.51.4"},"reference-count":78,"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\/iccv51701.2025.01461","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15748-15759","source":"Crossref","is-referenced-by-count":1,"title":["Zero-Shot Depth Aware Image Editing With Diffusion Models"],"prefix":"10.1109","author":[{"given":"Rishubh","family":"Parihar","sequence":"first","affiliation":[{"name":"IISc,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sachidanand","family":"VS","sequence":"additional","affiliation":[{"name":"IISc,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R. Venkatesh","family":"Babu","sequence":"additional","affiliation":[{"name":"IISc,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref3","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref5","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","volume-title":"arXiv preprint","author":"Meng","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02107"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00846"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_21"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687612"},{"key":"ref10","article-title":"Fluxspace: Disentangled semantic editing in rectified flow transformers","author":"Dalva","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3658150"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_9"},{"key":"ref13","article-title":"Layerfusion: Harmonized multi-layer text-to-image generation with generative priors","author":"Dalva","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00716"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3610543.3626172"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00617"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_40"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref20","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in neural information processing systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref21","article-title":"Layered rendering diffusion model for zero-shot guided image synthesis","volume-title":"arXiv preprint","author":"Qi","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00716"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02115"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00822"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00610"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32194"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00043"},{"issue":"2","key":"ref29","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0714"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00735"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref33","article-title":"Storydiffusion: Consistent selfattention for long-range image and video generation","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3618342"},{"key":"ref36","article-title":"p+: Extended textual conditioning in text-toimage generation","author":"Voynov","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3618322"},{"key":"ref38","article-title":"Diffusion models already have a semantic latent space","author":"Kwon","year":"2022","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1102"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01235"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_27"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00637"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02658"},{"key":"ref44","volume-title":"Improving Projective Geometry in Diffusion Models","author":"Upadhyay","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657525"},{"key":"ref47","article-title":"Object 3dit: Language-guided 3d-aware image editing","volume":"36","author":"Michel","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00056"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_25"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00811"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00266"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00406"},{"key":"ref53","article-title":"3ditscene: Editing any scene via language-guided disentangled gaussian splatting","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Customizing text-to-image diffusion with camera viewpoint control","author":"Kumari","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687611"},{"key":"ref56","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01756"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_9"},{"key":"ref60","article-title":"Magic insert: Style-aware drag-and-drop","author":"Ruiz","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_7"},{"key":"ref62","article-title":"Inserf: Text-driven generative object insertion in neural 3d scenes","author":"Shahbazi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0746"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591560"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00091"},{"key":"ref67","article-title":"Motion guidance: Diffusion-based image editing with differentiable motion estimators","volume-title":"The Twelfth International Conference on Learning Representations","author":"Geng"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00785"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref70","article-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth","author":"Farooq Bhat","year":"2023","journal-title":"arXiv preprint"},{"key":"ref71","year":"2022","journal-title":"vit-swin-base-224-gpt2-image-captioning"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00479"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref74","article-title":"Demystifying MMD GANs","volume-title":"International Conference on Learning Representations","author":"Bi\u0144kowski","year":"2018"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref76","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"}],"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\/11445754.pdf?arnumber=11445754","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:16:56Z","timestamp":1777612616000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445754\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01461","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}