Tag
This paper presents a 3D-aware neural approach for RGB-NIR low-light imaging that fuses extremely noisy RGB observations with NIR cues in 3D space, eliminating the need for clean RGB supervision and improving robustness across different noise levels.
ControlLight is a controllable low-light enhancement framework that uses a large-scale real-world dataset and a weighted flow matching loss to achieve consistent image quality across varying enhancement strengths, achieving state-of-the-art performance.
M2Retinexformer extends the Retinexformer framework for low-light image enhancement by incorporating depth, luminance, and semantic cues via cross-attention and adaptive gating, achieving state-of-the-art results on multiple benchmarks.
PrunaAI's P-Image-Upscale is an AI model for fast image upscaling up to 8 megapixels, offering target and factor modes with optional realism and detail enhancements.