-
arXiv 2026
We present SAFE, a novel color constancy framework for pure-color scenes with (1) a scene-aware feature modulation network and (2) the Learned Color Space (LCS) that directly addresses the chromaticity collapse problem when scene color distributions become too uniform.
-
arXiv 2026
We present BOCCHI, a real-captured local motion blur detection benchmark of 633 pixel-annotated images featuring textured blurred regions that defeat gradient-based shortcuts. We also propose MSDCT-UNet, a frequency-aware encoder–decoder that reads blur in the DCT domain via multi-scale DCT attention and FiLM modulation.
-
RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes
ECCV 2026
We present RL-AWB, a novel framework combining statistical methods with deep reinforcement learning for nighttime white balance. We also contribute LEVI, the first multi-sensor nighttime dataset for color constancy in this work.
-
IEEE APCCAS 2025
FRIEREN, a novel no-reference image quality assessment, effectively and accurately evaluates the face detail quality scaled by different interpolations with low computational complexity.