Rethinking Underwater Image Enhancement: Learning through Text-Guided Degradation Curriculum

The paper introduces a unified training framework for underwater image enhancement that addresses the scarcity of paired clean-degraded datasets. It employs a text-guided diffusion model to generate diverse, semantically consistent degraded images and uses a progressive degradation curriculum to balance learning across multiple attributes and difficulty levels. The approach also incorporates a transmission-guided one-step diffusion model to handle varying degradation severity, achieving superior performance on several underwater benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• diffusion
• benchmarks