TL;DR
This paper introduces Ucolor, an underwater image enhancement network that combines multi-color space embedding and medium transmission guidance to effectively improve underwater image quality, outperforming existing methods.
Contribution
The paper proposes a novel multi-color space encoder with attention and a medium transmission-guided decoder, integrating physical models with learning for superior underwater image enhancement.
Findings
Ucolor outperforms state-of-the-art methods in visual quality.
The multi-color space encoder enhances feature diversity.
Medium transmission guidance improves focus on degraded regions.
Abstract
Underwater images suffer from color casts and low contrast due to wavelength- and distance-dependent attenuation and scattering. To solve these two degradation issues, we present an underwater image enhancement network via medium transmission-guided multi-color space embedding, called Ucolor. Concretely, we first propose a multi-color space encoder network, which enriches the diversity of feature representations by incorporating the characteristics of different color spaces into a unified structure. Coupled with an attention mechanism, the most discriminative features extracted from multiple color spaces are adaptively integrated and highlighted. Inspired by underwater imaging physical models, we design a medium transmission (indicating the percentage of the scene radiance reaching the camera)-guided decoder network to enhance the response of the network towards quality-degraded…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
