arXiv Computer Vision By Jieyu Yuan, Yuanlin Zhang, Jihong Li, Chunle Guo, Huimin Lu, Chongyi Li

3D-USE: From Image-Level to Scene-Level Underwater Enhancement

Read the original on arXiv Computer Vision →

The paper introduces 3D-USE, a two‑stage framework for underwater scene‑level enhancement that learns a persistent, visibility‑enhanced 3D representation from degraded multi‑view observations. First, the Medium Radial Basis Anchor Representation (MediumRBF) builds a medium‑aware Gaussian scene by separating object and medium effects. Then, Appearance Transition Consensus (ATC) transfers 2D underwater image enhancement knowledge into scene‑global and Gaussian‑local targets, which are realized by an Underwater Bilateral Appearance Field (U‑BAF) to render enhanced novel views without a 2D UIE model at inference. Experiments on real underwater scenes demonstrate improved visibility, cross‑view consistency, and preserved reconstruction quality.

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.

Hugging Face Trending Papers
Jul 23

WAT3R: Feedforward Underwater 3D Reconstruction

Reliable feedforward underwater 3D reconstruction remains challenging due to severe light attenuation and backscattering, which degrade visual quality and disrupt feature consistency across views, leading to inaccurate multi-view geometry. To address this issue, we propose WAT3R, a feed-forward framework for reconstructing 3D scenes directly from underwater images.