Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model
Keda Tao, Jinjin Gu, Yulun Zhang, Xiucheng Wang, Nan Cheng
2025Year
5Top-tier citations
Abstract
Published as a conference paper at ICLR 2025 cesses, enhancing the accuracy of identity preservation and attribute correction. Including negative quality samples and attribute prompts in the training further refines the model's ability to generate detailed and perceptually accurate images.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 246bf9c1-2936-4274-bf91-e3286984e9f8Cited by top-tier papers5
- RefSTAR: Blind Face Image Restoration with Reference Selection, Transfer, and ReconstructionZhicun Yin, Junjie Chen, Ming Liu, Zhixin Wang et al.AAAI 2026 · 2 citations
- Steering Where to Diffuse: Generative Modeling of Phenotypic Response Simulation with Steered Diffusion BridgeRongchao Zhang, Chengxin Li, Yiwei Lou, Yuling Shi et al.CVPR 2026 · 1 citation
- Show and Polish: Reference-Guided Identity Preservation in Face Video RestorationWenkang Han, Wang Lin, Yiyun Zhou, Qi Liu et al.ACM MM 2025 · 1 citation
- Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene RestorationAmirhossein Kazerouni, Maitreya Suin, Tristan T Aumentado-Armstrong, Sina Honari et al.CVPR 2026
- UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion ModelsFanghua Yu, Jinjin Gu, Jinfan Hu, Zheyuan Li et al.ICLR 2025
Builds on22
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 citations
- T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion ModelsChong Mou, Xintao Wang, Liangbin Xie, Yanze Wu et al.AAAI 2024 · 1,641 citations
- MUSIQ: Multi-scale Image Quality TransformerJunjie Ke, Qifei Wang, Yilin Wang, Peyman Milanfar et al.ICCV 2021 · 1,325 citations
Related papers
- ObjectStitch: Object Compositing with Diffusion ModelYizhi Song, Zhifei Zhang, Zhe Lin, Scott Cohen et al.CVPR 2023
- Multimodal Large Language Models Make Text-to-Image Generative Models Align BetterXun Wu, Shaohan Huang, Guolong Wang, Jing Xiong et al.NeurIPS 2024 · 26 citations
- Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic DirectionsStefan Andreas Baumann, Felix Krause, Michael Neumayr, Nick Stracke et al.CVPR 2025
- CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion ModelsZheng Chong, Xiao Dong, Haoxiang Li, Shiyue Zhang et al.ICLR 2025
- Devil is in the Detail: Towards Injecting Fine Details of Image Prompt in Image Generation via Conflict-free Guidance and Stratified AttentionKyungmin Jo, Jooyeol Yun, Jaegul ChooCVPR 2025
