AI RESEARCH
A Physically-Grounded Attack and Adaptive Defense Framework for Real-World Low-Light Image Enhancement
arXiv CS.CV
•
ArXi:2603.14304v1 Announce Type: new Limited illumination often causes severe physical noise and detail degradation in images. Existing Low-Light Image Enhancement (LLIE) methods frequently treat the enhancement process as a blind black-box mapping, overlooking the physical noise transformation during imaging, leading to suboptimal performance. To address this, we propose a novel LLIE approach, conceptually formulated as a physics-based attack and display-adaptive defense paradigm. Specifically, on the attack side, we establish a physics-based Degradation Synthesis (PDS) pipeline.