Abstract: Image highlight removal is a fundamental and challenging visual task. Although fully supervised deep learning-based methods have achieved remarkable results, their performance is limited by ...
We are excited to release the CapRL 2.0 series: CapRL-Qwen3VL-2B and CapRL-Qwen3VL-4B. These models feature fewer parameters while delivering even more powerful captioning performance. Notably, ...
Abstract: Low-light image enhancement (LIE) aims to restore images taken under poor lighting conditions, thereby extracting more information and details to robustly support subsequent visual tasks.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback