Multi-modal degradation feature learning for unified image restoration based on contrastive learning
L Chen, Q Xiong, W Zhang, X Liang, Z Gan, L Li, X He - Neurocomputing, 2025 - Elsevier
In this paper, we address the unified image restoration challenge by reframing it as a
contrastive learning-based classification problem. Despite the significant strides made by …
contrastive learning-based classification problem. Despite the significant strides made by …
DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
Image restoration (IR) in real-world scenarios presents significant challenges due to the lack
of high-capacity models and comprehensive datasets. To tackle these issues, we present a …
of high-capacity models and comprehensive datasets. To tackle these issues, we present a …