{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:08:22Z","timestamp":1784268502138,"version":"3.55.0"},"reference-count":50,"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"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["113-2221-E-006-161-MY3"],"award-info":[{"award-number":["113-2221-E-006-161-MY3"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01403","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15117-15126","source":"Crossref","is-referenced-by-count":1,"title":["MaTe: Images are All You Need for Material Transfer via Diffusion Transformer"],"prefix":"10.1109","author":[{"given":"Nisha","family":"Huang","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henglin","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhou","family":"Lin","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaer","family":"Huang","sequence":"additional","affiliation":[{"name":"Lenovo Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chubin","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Guo","sequence":"additional","affiliation":[{"name":"PengCheng Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong-Yee","family":"Lee","sequence":"additional","affiliation":[{"name":"National Cheng-Kung University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"ref2","article-title":"Pixart-$\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_21"},{"key":"ref4","article-title":"Catvton: Concatenation is all you need for virtual try-on with diffusion models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Chong"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201378"},{"key":"ref6","volume-title":"controlnet-depth-sdxl-1.0"},{"key":"ref7","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref8","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"The Eleventh International Conference on Learning Representations","author":"Gal"},{"key":"ref9","article-title":"Materialfusion: High-quality, zero-shot, and controllable material transfer with diffusion models","author":"Garifullin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480507"},{"key":"ref11","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"The Eleventh International Conference on Learning Representations","author":"Hertz"},{"key":"ref12","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"The Tenth International Conference on Learning Representations","author":"Hu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356516"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3502431"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548282"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3342645"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3570771"},{"key":"ref18","article-title":"Artcrafter: Text-image aligning style transfer via embedding reframing","author":"Huang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref19","volume-title":"Unsplash"},{"key":"ref20","article-title":"Auto-encoding variational bayes","volume-title":"The Second International Conference on Learning Representations","author":"Kingma"},{"key":"ref21","volume-title":"Flux"},{"key":"ref22","volume-title":"Flux.1-depth-dev-lora"},{"key":"ref23","volume-title":"Flux.1-dev-controlnet-depth"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4095"},{"key":"ref25","article-title":"Flow matching for generative modeling","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lipman"},{"key":"ref26","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"The Eleventh International Conference on Learning Representations","author":"Liu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00419"},{"key":"ref28","volume-title":"Qwen2vl-flux: Unifying image and text guidance for controllable image generation","author":"Lu","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1653"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref32","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell"},{"key":"ref33","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":"ref34","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591503"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02278"},{"key":"ref39","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00906"},{"key":"ref43","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3032734"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00412"},{"key":"ref46","volume-title":"Controlnet-v1.1-depth","author":"Zhang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3618342"},{"key":"ref50","volume-title":"Evf-sam: Early vision-language fusion for textprompted segment anything model","author":"Zhang","year":"2024"}],"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\/11446002.pdf?arnumber=11446002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:35:55Z","timestamp":1777530955000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446002\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01403","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}