Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a unified, unsupervised framework for enhancing backlit and low-light images, addressing the common issues of exposure imbalance and global underexposure without the need for paired ground-truth data. Leveraging CLIP-guided prompt learning and a symmetric residual U-Net architecture with an Atrous Spatial Pyramid Pooling module, the method captures multi-scale contextual information for adaptive correction. Experimental results demonstrate superior performance over existing state-of-the-art methods in fidelity, perceptual quality, and generalization across various datasets, highlighting the framework's robustness in real-world applications.
Unsupervised image enhancement can now effectively tackle both backlit and low-light conditions without paired data, outperforming traditional methods.
Backlit and low-light images often suffer from severe exposure imbalance or global underexposure, presenting significant challenges for both visual perception and downstream computer vision tasks. In this paper, we propose a unified, unsupervised enhancement framework that addresses both types of degradation without relying on paired ground-truth data. Our approach builds on CLIP-guided prompt learning to semantically supervise enhancement using learned positive and negative textual prompts. To improve the quality of our improvements over prior work, we design a symmetric residual U-Net backbone augmented with an Atrous Spatial Pyramid Pooling module. This architecture captures multi-scale contextual information, enabling adaptive correction under spatially heterogeneous illumination. During training, the enhancement network is guided by CLIP-based semantic similarity losses and refined via an iterative prompt optimization mechanism. Extensive experiments on both paired and unpaired datasets, including BAID, Backlit300, LOL, and VE-LOL-L, demonstrate that our framework consistently outperforms state-of-the-art supervised and unsupervised methods in terms of fidelity, perceptual quality, and generalization. Furthermore, our work emphasizes the need for stronger benchmarking protocols for backlit enhancement, a relatively underexplored area. The proposed framework provides a robust, scalable solution for real-world illumination enhancement across diverse lighting conditions.