{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:29:25Z","timestamp":1776886165073,"version":"3.51.2"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015805","name":"Shenzhen Municipal Science and Technology Innovation Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100015805","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890576","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Dual Encoders for Diffusion-based Image Inpainting"],"prefix":"10.1109","author":[{"given":"Dezhi","family":"Zheng","sequence":"first","affiliation":[{"name":"Shenzhen University,Computer Vision Institute, School of Computer Science and Software Engineering,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaijun","family":"Deng","sequence":"additional","affiliation":[{"name":"Shenzhen University,Computer Vision Institute, School of Computer Science and Software Engineering,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinbao","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen University,National Engineering Laboratory for Big Data System Computing Technology,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linlin","family":"Shen","sequence":"additional","affiliation":[{"name":"Shenzhen University,Computer Vision Institute, School of Computer Science and Software Engineering,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","article-title":"Hunyuan-dit: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding","author":"Li","year":"2024"},{"key":"ref3","article-title":"Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis","author":"Team","year":"2024"},{"key":"ref4","article-title":"stable-diffusion-2-inpainting","year":"2024"},{"key":"ref5","article-title":"Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref7","article-title":"Pixart-\u03b4: Fast and controllable image generation with latent consistency models","author":"Chen","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref11","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref12","article-title":"Neural discrete representation learning","volume":"30","author":"Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume":"32","author":"Razavi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618149"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00636"},{"key":"ref16","article-title":"stable-diffusion-2-inpainting","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073659"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01371"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_14"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01113"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108415"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00674"},{"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","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_9"},{"key":"ref26","article-title":"Designing a better asymmetric vqgan for stablediffusion","author":"Zhu","year":"2023"},{"key":"ref27","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_12"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref31","article-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth","author":"Bhat","year":"2023"},{"key":"ref32","article-title":"Open3d: A modern library for 3d data processing","author":"Zhou","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890576.pdf?arnumber=10890576","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:54Z","timestamp":1774416234000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890576\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890576","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}