AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement
원문 초록
Existing low-light image enhancement (LIE) methods have achieved noteworthy success in solving synthetic distortions, yet they often fall short in practical applications. The limitations arise from two inherent challenges in real-world LIE: 1) the collection of distorted/clean image pairs is often impractical and sometimes even unavailable, and 2) accurately modeling complex degradations presents a non-trivial problem. To overcome them, we propose the Attribute Guidance Diffusion framework (AGLLDiff), a training-free method for effective real-world LIE. Instead of specifically defining the degradation process, AGLLDiff shifts the paradigm and models the desired attributes, such as image exposure, structure and color of normal-light images. These attributes are readily available and impose no assumptions about the degradation process, which guides the diffusion sampling process to a reliable high-quality solution space. Extensive experiments demonstrate that our approach outperforms the current leading unsupervised LIE methods across benchmarks in terms of distortion-based and perceptual-based metrics, and it performs well even in sophisticated wild degradation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
PDE: Gene Effect Inspired Parameter Dynamic Evolution for Low-light Image Enhancement
HVI-CIDNet+: Beyond Extreme Darkness for Low-Light Image Enhancement
RT-X Net: RGB-Thermal cross attention network for Low-Light Image Enhancement
URWKV: Unified RWKV Model with Multi-state Perspective for Low-light Image Restoration
See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction
Degradation-Aware Feature Perturbation for All-in-One Image Restoration
토론
이 논문과 연결된 포럼 글이 아직 없습니다.