Hugging Face Trending Papers

BlindPSNR: A No-Reference Fidelity Predictor for Low-Light Image Enhancement

Read the original on Hugging Face Trending Papers →

Low-light image enhancement (LLIE) methods involve tunable parameters that are typically fixed, often leading to performance degradation when applied across scenes. Manually selecting the best configuration, however, can be time-consuming and not always practical.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

Hugging Face Trending Papers
Jun 29

LEIQ-Assessor: Multi-dimensional Quality Assessment of Low-light Enhanced Images via Multi-task Learning

Low-light image enhancement algorithms (LIEAs) aim to improve the visibility of images captured under poor illumination. However, the enhancement process often introduces artifacts such as noise amplification, color shift, structural damage, and over-exposure, which degrade the perceptual quality of the enhanced images.