UniDemoiré creates large, diverse, realistic moiré training images and shows that downstream demoiréing models trained on them generalize better to new domains.
Convolutional Color Constancy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Color constancy is the problem of inferring the color of the light that illuminated a scene, usually so that the illumination color can be removed. Because this problem is underconstrained, it is often solved by modeling the statistical regularities of the colors of natural objects and illumination. In contrast, in this paper we reformulate the problem of color constancy as a 2D spatial localization task in a log-chrominance space, thereby allowing us to apply techniques from object detection and structured prediction to the color constancy problem. By directly learning how to discriminate between correctly white-balanced images and poorly white-balanced images, our model is able to improve performance on standard benchmarks by nearly 40%.
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
UniDemoir\'e: Towards Universal Image Demoir\'eing with Data Generation and Synthesis
UniDemoiré creates large, diverse, realistic moiré training images and shows that downstream demoiréing models trained on them generalize better to new domains.