{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:45Z","timestamp":1777865325359,"version":"3.51.4"},"reference-count":59,"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\/iccv51701.2025.00764","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8154-8164","source":"Crossref","is-referenced-by-count":0,"title":["CObL: Toward Zero-Shot Ordinal Layering Without User Prompting"],"prefix":"10.1109","author":[{"given":"Aneel","family":"Damaraju","sequence":"first","affiliation":[{"name":"Harvard University, School of Engineering and Applied Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dean","family":"Hazineh","sequence":"additional","affiliation":[{"name":"Harvard University, School of Engineering and Applied Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Todd","family":"Zickler","sequence":"additional","affiliation":[{"name":"Harvard University, School of Engineering and Applied Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref2","article-title":"Slot-guided adaptation of pre-trained diffusion models for object-centric learning and compositional generation","author":"Akan","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811646"},{"key":"ref4","article-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","author":"Bar-Tal","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref5","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv"},{"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","article-title":"MONet: Unsupervised scene decomposition and representation","author":"Burgess","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1565"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00428"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00547"},{"key":"ref13","article-title":"Reduce, reuse, recycle:Compositional generation with energy-based diffusion models and mcmc","volume-title":"International conference on machine learning","author":"Du"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00146"},{"key":"ref15","article-title":"An image is worth one word: Personalizing text-toimage generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref16","article-title":"Multi-object representation learning with iterative variational inference","volume-title":"International conference on machine learning","author":"Greff"},{"key":"ref17","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref19","first-page":"8633","article-title":"Fleet. Video diffusion models","volume":"35","author":"Ho","year":"2022","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248048"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref23","article-title":"Clevrtex: A texture-rich benchmark for unsupervised multiobject segmentation","author":"Karazija","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00401"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02053"},{"key":"ref30","article-title":"Syncdiffusion: Coherent montage via synchronized joint diffusions","author":"Lee","year":"2023","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref31","first-page":"16246","article-title":"Variational amodal object completion","volume":"33","author":"Ling","year":"2020","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref33","article-title":"Objectcentric learning with slot attention","author":"Locatello","year":"2020","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00852"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v38i5.28226","article-title":"T2iadapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models","author":"Mou","year":"2024","journal-title":"AAAI"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00377"},{"key":"ref39","article-title":"Vision science: Photons to phenomenology","author":"Palmer","year":"1999","journal-title":"MIT press"},{"key":"ref40","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref41","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00313"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404"},{"key":"ref45","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00914"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref49","article-title":"Bridging the gap to real-world object-centric learning","author":"Seitzer","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref50","article-title":"Denoising diffusion implicit models","author":"Song","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00341"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/800224.806813"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00869"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3390\/e25101469"},{"key":"ref56","article-title":"Learning visual parkour from generated images","volume-title":"8th Annual Conference on Robot Learning","author":"Yu"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02645"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00384"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.320"}],"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\/11446000.pdf?arnumber=11446000","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:16:10Z","timestamp":1777529770000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446000\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00764","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}