Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model
Keda Tao, Jinjin Gu, Yulun Zhang, Xiucheng Wang, Nan Cheng
2025年份
5顶会引用
摘要
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.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper5
- RefSTAR: Blind Face Image Restoration with Reference Selection, Transfer, and ReconstructionZhicun Yin, Junjie Chen, Ming Liu, Zhixin Wang 等AAAI 2026 · 被引用 2 次
- Steering Where to Diffuse: Generative Modeling of Phenotypic Response Simulation with Steered Diffusion BridgeRongchao Zhang, Chengxin Li, Yiwei Lou, Yuling Shi 等CVPR 2026 · 被引用 1 次
- Show and Polish: Reference-Guided Identity Preservation in Face Video RestorationWenkang Han, Wang Lin, Yiyun Zhou, Qi Liu 等ACM MM 2025 · 被引用 1 次
- Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene RestorationAmirhossein Kazerouni, Maitreya Suin, Tristan T Aumentado-Armstrong, Sina Honari 等CVPR 2026
- UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion ModelsFanghua Yu, Jinjin Gu, Jinfan Hu, Zheyuan Li 等ICLR 2025
它引用的顶会 Paper22
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 被引用 6,759 次
- T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion ModelsChong Mou, Xintao Wang, Liangbin Xie, Yanze Wu 等AAAI 2024 · 被引用 1,641 次
- MUSIQ: Multi-scale Image Quality TransformerJunjie Ke, Qifei Wang, Yilin Wang, Peyman Milanfar 等ICCV 2021 · 被引用 1,325 次
相关 Paper
- ObjectStitch: Object Compositing with Diffusion ModelYizhi Song, Zhifei Zhang, Zhe Lin, Scott Cohen 等CVPR 2023
- Multimodal Large Language Models Make Text-to-Image Generative Models Align BetterXun Wu, Shaohan Huang, Guolong Wang, Jing Xiong 等NeurIPS 2024 · 被引用 26 次
- Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic DirectionsStefan Andreas Baumann, Felix Krause, Michael Neumayr, Nick Stracke 等CVPR 2025
- CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion ModelsZheng Chong, Xiao Dong, Haoxiang Li, Shiyue Zhang 等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
