{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:46:45Z","timestamp":1774021605016,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,10]]},"DOI":"10.1145\/3721238.3730655","type":"proceedings-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T08:40:47Z","timestamp":1753260047000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Scene-Level Appearance Transfer with Semantic Correspondences"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4400-2289","authenticated-orcid":false,"given":"Liyuan","family":"Zhu","sequence":"first","affiliation":[{"name":"Stanford University, Stanford, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3063-9644","authenticated-orcid":false,"given":"Shengqu","family":"Cai","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5274-3407","authenticated-orcid":false,"given":"Shengyu","family":"Huang","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9243-6885","authenticated-orcid":false,"given":"Gordon","family":"Wetzstein","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9247-7897","authenticated-orcid":false,"given":"Naji","family":"Khosravan","sequence":"additional","affiliation":[{"name":"Zillow Group, Seattle, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4230-5916","authenticated-orcid":false,"given":"Iro","family":"Armeni","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657423"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00727"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00204"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_3_2_7_1","volume-title":"ECCV","author":"Cheng Xinle","year":"2024","unstructured":"Xinle Cheng, Congyue Deng, Adam Harley, Yixin Zhu, and Leonidas Guibas. 2024. Zero-Shot Image Feature Consensus with Deep Functional Maps. In ECCV."},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"e_1_3_3_2_9_1","volume-title":"arXiv","author":"Chung Jaeyoung","year":"2023","unstructured":"Jaeyoung Chung, Suyoung Lee, Hyeongjin Nam, Jaerin Lee, and Kyoung\u00a0Mu Lee. 2023. LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes. In arXiv."},{"key":"e_1_3_3_2_10_1","volume-title":"ICLR","author":"Darcet Timoth\u00e9e","year":"2024","unstructured":"Timoth\u00e9e Darcet, Maxime Oquab, Julien Mairal, and Piotr Bojanowski. 2024. Vision Transformers Need Registers. In ICLR."},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657513"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2686"},{"key":"e_1_3_3_2_13_1","volume-title":"ICLR","author":"Dumoulin Vincent","year":"2017","unstructured":"Vincent Dumoulin, Ishmael Belghazi, Ben Poole, Alex Lamb, Martin Arjovsky, Olivier Mastropietro, and Aaron Courville. 2017. Adversarially Learned Inference. In ICLR."},{"key":"e_1_3_3_2_14_1","volume-title":"NeurIPS","author":"Epstein Dave","year":"2023","unstructured":"Dave Epstein, Allan Jabri, Ben Poole, Alexei\u00a0A. Efros, and Aleksander Holynski. 2023. Diffusion Self-Guidance for Controllable Image Generation. In NeurIPS."},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00214"},{"key":"e_1_3_3_2_17_1","volume-title":"NeurIPS","author":"Fu Stephanie","year":"2023","unstructured":"Stephanie Fu, Netanel Tamir, Shobhita Sundaram, Lucy Chai, Richard Zhang, Tali Dekel, and Phillip Isola. 2023. DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data. In NeurIPS."},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687643"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_3_2_20_1","unstructured":"Sooyeon Go Kyungmook Choi Minjung Shin and Youngjung Uh. 2024. Eye-for-an-eye: Appearance Transfer with Semantic Correspondence in Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2406.07008"},{"key":"e_1_3_3_2_21_1","unstructured":"Eric Hedlin Gopal Sharma Shweta Mahajan Xingzhe He Hossam Isack Abhishek Kar\u00a0Helge Rhodin Andrea Tagliasacchi and Kwang\u00a0Moo Yi. 2023. Unsupervised Keypoints from Pretrained Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.00065 (2023)."},{"key":"e_1_3_3_2_22_1","volume-title":"arXiv","author":"Hertz Amir","year":"2022","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-Or. 2022. Prompt-to-prompt image editing with cross attention control. In arXiv."},{"key":"e_1_3_3_2_23_1","volume-title":"NeuIPS","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, G\u00fcnter Klambauer, and Sepp Hochreiter. 2017. GANs Trained by a Two Time-Scale Update Rule Converge to a Nash Equilibrium. In NeuIPS."},{"key":"e_1_3_3_2_24_1","volume-title":"NeurIPS","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In NeurIPS."},{"key":"e_1_3_3_2_25_1","volume-title":"NeurIPS Workshop","author":"Ho Jonathan","year":"2021","unstructured":"Jonathan Ho and Tim Salimans. 2021. Classifier-Free Diffusion Guidance. In NeurIPS Workshop."},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"e_1_3_3_2_28_1","volume-title":"arXiv","author":"Jin Haian","year":"2024","unstructured":"Haian Jin, Hanwen Jiang, Hao Tan, Kai Zhang, Sai Bi, Tianyuan Zhang, Fujun Luan, Noah Snavely, and Zexiang Xu. 2024. LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias. In arXiv."},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimk\u00fchler and George Drettakis. 2023. 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42 4 (2023) 139\u20131.","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_2_31_1","volume-title":"arXiv","author":"Koh Jing\u00a0Yu","year":"2022","unstructured":"Jing\u00a0Yu Koh, Harsh Agrawal, Dhruv Batra, Richard Tucker, Austin Waters, Honglak Lee, Yinfei Yang, Jason Baldridge, and Peter Anderson. 2022. Simple and Effective Synthesis of Indoor 3D Scenes. In arXiv."},{"key":"e_1_3_3_2_32_1","volume-title":"arXiv","author":"Li Shaoxu","year":"2024","unstructured":"Shaoxu Li. 2024. DiffStyler: Diffusion-based Localized Image Style Transfer. In arXiv."},{"key":"e_1_3_3_2_33_1","volume-title":"arXiv","author":"Li Senmao","year":"2023","unstructured":"Senmao Li, Joost van\u00a0de Weijer, Taihang Hu, Fahad\u00a0Shahbaz Khan, Qibin Hou, Yaxing Wang, and Jian Yang. 2023. StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing. In arXiv."},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01419"},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/8579.003.0031"},{"key":"e_1_3_3_2_36_1","volume-title":"arXiv","author":"Liu Fangfu","year":"2024","unstructured":"Fangfu Liu, Wenqiang Sun, Hanyang Wang, Yikai Wang, Haowen Sun, Junliang Ye, Jun Zhang, and Yueqi Duan. 2024a. ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model. In arXiv."},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3681758.3698002"},{"key":"e_1_3_3_2_38_1","volume-title":"ICLR","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In ICLR."},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"crossref","unstructured":"David\u00a0G. Lowe. 2004. Distinctive Image Features from Scale-Invariant Keypoints. IJCV.","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"e_1_3_3_2_40_1","volume-title":"ICLR","author":"Meng Chenlin","year":"2022","unstructured":"Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. 2022. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. In ICLR."},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul\u00a0P Srinivasan Matthew Tancik Jonathan\u00a0T Barron Ravi Ramamoorthi and Ren Ng. 2021. Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM (2021).","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00548"},{"key":"e_1_3_3_2_43_1","volume-title":"TMLR","author":"Oquab Maxime","year":"2024","unstructured":"Maxime Oquab, Timoth\u00e9e Darcet, Th\u00e9o Moutakanni, Huy\u00a0V. Vo, Marc Szafraniec, et\u00a0al. 2024. DINOv2: Learning Robust Visual Features without Supervision. In TMLR."},{"key":"e_1_3_3_2_44_1","volume-title":"Arxiv","author":"Ouyang Hao","year":"2023","unstructured":"Hao Ouyang, Tiancheng Sun, Stephen Lombardi, and Kathryn Heal. 2023. Text2Immersion: Generative Immersive Scene with 3D Gaussians. In Arxiv."},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"crossref","unstructured":"Bo\u00a0Hyeon Park and Kyung\u00a0Hoon Hyun. 2022. Analysis of pairings of colors and materials of furnishings in interior design with a data-driven framework. Journal of Computational Design and Engineering 9 6 (2022) 2419\u20132438.","DOI":"10.1093\/jcde\/qwac114"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687611"},{"key":"e_1_3_3_2_47_1","volume-title":"ICLR","author":"Podell Dustin","year":"2024","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2024. SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. In ICLR."},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01384"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01409"},{"key":"e_1_3_3_2_51_1","volume-title":"NeurIPS","author":"Seo Junyoung","year":"2024","unstructured":"Junyoung Seo, Kazumi Fukuda, Takashi Shibuya, Takuya Narihira, Naoki Murata, Shoukang Hu, Chieh-Hsin Lai, Seungryong Kim, and Yuki Mitsufuji. 2024. GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping. In NeurIPS."},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00086"},{"key":"e_1_3_3_2_53_1","volume-title":"arXiv","author":"Sun Wenqiang","year":"2024","unstructured":"Wenqiang Sun, Shuo Chen, Fangfu Liu, Zilong Chen, Yueqi Duan, Jun Zhang, and Yikai Wang. 2024. DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion. In arXiv."},{"key":"e_1_3_3_2_54_1","volume-title":"NeurIPS","author":"Tang Luming","year":"2023","unstructured":"Luming Tang, Menglin Jia, Qianqian Wang, Cheng\u00a0Perng Phoo, and Bharath Hariharan. 2023. Emergent Correspondence from Image Diffusion. In NeurIPS."},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01609"},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"crossref","unstructured":"Narek Tumanyan Omer Bar-Tal Shir Amir Shai Bagon and Tali Dekel. 2023a. Disentangling Structure and Appearance in ViT Feature Space. ACM Trans. Graph. (nov 2023).","DOI":"10.1145\/3630096"},{"key":"e_1_3_3_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"e_1_3_3_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"e_1_3_3_2_59_1","volume-title":"SIGGRAPH","author":"\u0160ubrtov\u00e1 Ad\u00e9la","year":"2023","unstructured":"Ad\u00e9la \u0160ubrtov\u00e1, Michal Luk\u00e1\u010d, Jan \u010cech, David Futschik, Eli Shechtman, and Daniel S\u00fdkora. 2023. Diffusion Image Analogies. In SIGGRAPH."},{"key":"e_1_3_3_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"e_1_3_3_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_3_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00749"},{"key":"e_1_3_3_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"e_1_3_3_2_64_1","volume-title":"NeurIPS","author":"Yang Lihe","year":"2024","unstructured":"Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao, Xiaogang Xu, Jiashi Feng, and Hengshuang Zhao. 2024. Depth Anything V2. In NeurIPS."},{"key":"e_1_3_3_2_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02091"},{"key":"e_1_3_3_2_66_1","volume-title":"arXiv","author":"Ye Hu","year":"2023","unstructured":"Hu Ye, Jun Zhang, Sibo Liu, Xiao Han, and Wei Yang. 2023. Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. In arXiv."},{"key":"e_1_3_3_2_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00653"},{"key":"e_1_3_3_2_68_1","volume-title":"arXiv","author":"Yu Wangbo","year":"2024","unstructured":"Wangbo Yu, Jinbo Xing, Li Yuan, Wenbo Hu, Xiaoyu Li, Zhipeng Huang, Xiangjun Gao, Tien-Tsin Wong, Ying Shan, and Yonghong Tian. 2024. ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis. In arXiv."},{"key":"e_1_3_3_2_69_1","volume-title":"NeurIPS","author":"Zhang Junyi","year":"2023","unstructured":"Junyi Zhang, Charles Herrmann, Junhwa Hur, Luisa\u00a0Polania Cabrera, Varun Jampani, Deqing Sun, and Ming-Hsuan Yang. 2023a. A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence. In NeurIPS."},{"key":"e_1_3_3_2_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_2_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"e_1_3_3_2_73_1","volume-title":"NeurIPS","author":"Zhou Yupeng","year":"2024","unstructured":"Yupeng Zhou, Daquan Zhou, Ming-Ming Cheng, Jiashi Feng, and Qibin Hou. 2024. StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation. In NeurIPS."}],"event":{"name":"SIGGRAPH Conference Papers '25: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Vancouver BC Canada","acronym":"SIGGRAPH Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721238.3730655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T14:51:34Z","timestamp":1774018294000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721238.3730655"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":72,"alternative-id":["10.1145\/3721238.3730655","10.1145\/3721238"],"URL":"https:\/\/doi.org\/10.1145\/3721238.3730655","relation":{},"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}