Dream-IF: Dynamic Relative EnhAnceMent for Image Fusion
摘要
Image fusion aims to integrate comprehensive information from images acquired through multiple sources. However, images captured by diverse sensors often encounter various degradations that can negatively affect fusion quality. Traditional fusion methods generally treat image enhancement and fusion as separate processes, overlooking the inherent correlation between them; notably, the dominant regions in one modality of a fused image often indicate areas where the other modality might benefit from enhancement. Inspired by this observation, we introduce the concept of dominant regions for image enhancement and present a Dynamic Relative En-hAnceMent framework for Image Fusion (Dream-IF). This framework quantifies the relative dominance of each modality across different layers and leverages this information to facilitate reciprocal cross-modal enhancement. By integrating the relative dominance derived from image fusion, our approach supports not only image restoration but also a broader range of image enhancement applications. Furthermore, we employ prompt-based encoding to capture degradation-specific details, which dynamically steer the restoration process and promote coordinated enhancement in both multi-modal image fusion and image enhancement scenarios. Extensive experimental results demonstrate that Dream-IF consistently outperforms its counterparts. The code is publicly available. 1
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
脉络
- Restormer: Efficient Transformer for High-Resolution Image Restoration 引用了 Uformer: A General U-Shaped Transformer for Image Restoration
- PromptIR: Prompting for All-in-One Image Restoration 引用了 Uformer: A General U-Shaped Transformer for Image Restoration
- PromptIR: Prompting for All-in-One Image Restoration 引用了 Designing a Practical Degradation Model for Deep Blind Image Super-Resolution
- PromptIR: Prompting for All-in-One Image Restoration 引用了 Restormer: Efficient Transformer for High-Resolution Image Restoration
它引用的 Paper14
- Restormer: Efficient Transformer for High-Resolution Image RestorationSyed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat 等CVPR 2022 · 3,348 次引用
- Uformer: A General U-Shaped Transformer for Image RestorationZhendong Wang, Xiaodong Cun, Jianmin Bao, Wengang Zhou 等CVPR 2022 · 1,970 次引用
- Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object DetectionJinyuan Liu, Xin Fan, Zhanbo Huang, Guanyao Wu 等CVPR 2022 · 929 次引用
- Designing a Practical Degradation Model for Deep Blind Image Super-ResolutionKai Zhang, Jingyun Liang, Luc Van Gool, Radu TimofteICCV 2021 · 898 次引用
- PromptIR: Prompting for All-in-One Image RestorationVaishnav Potlapalli, Syed Waqas Zamir, Salman H. Khan, Fahad Shahbaz KhanNeurIPS 2023 · 386 次引用
相关 Paper
- Two Challenges, One Solution: Robust Multimodal Learning through Dynamic Modality Recognition and EnhancementLanxin Bi, Yunqi Zhang, Luyi Wang, Yake Niu 等EMNLP Findings 2025 · 2 次引用
- ReCoFuse: Ultra-Robust Image Fusion via Restorative Multi-Modal Diffusion Reciprocal CouplingHao Zhang, Shuhan Yang, Linfeng Tang, Xunpeng Yi 等CVPR 2026
- Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image FusionXunpeng Yi, Han Xu, Hao Zhang, Linfeng Tang 等CVPR 2024 · 121 次引用
- Test-Time Dynamic Image FusionBing Cao, Yinan Xia, Yi Ding, Changqing Zhang 等NeurIPS 2024 · 13 次引用
- Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion ModelHao Zhang, Lei Cao, Jiayi MaNeurIPS 2024 · 69 次引用
