Enhancing Underwater Light Field Images via Global Geometry-aware Diffusion Process

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lin, Yuji, Zhao, Qian, Yue, Zongsheng, Hou, Junhui, Meng, Deyu
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908795993587712
author Lin, Yuji
Zhao, Qian
Yue, Zongsheng
Hou, Junhui
Meng, Deyu
author_facet Lin, Yuji
Zhao, Qian
Yue, Zongsheng
Hou, Junhui
Meng, Deyu
contents This work studies the challenging problem of acquiring high-quality underwater images via 4-D light field (LF) imaging. To this end, we propose GeoDiff-LF, a novel diffusion-based framework built upon SD-Turbo to enhance underwater 4-D LF imaging by leveraging its spatial-angular structure. GeoDiff-LF consists of three key adaptations: (1) a modified U-Net architecture with convolutional and attention adapters to model geometric cues, (2) a geometry-guided loss function using tensor decomposition and progressive weighting to regularize global structure, and (3) an optimized sampling strategy with noise prediction to improve efficiency. By integrating diffusion priors and LF geometry, GeoDiff-LF effectively mitigates color distortion in underwater scenes. Extensive experiments demonstrate that our framework outperforms existing methods across both visual fidelity and quantitative performance, advancing the state-of-the-art in enhancing underwater imaging. The code will be publicly available at https://github.com/linlos1234/GeoDiff-LF.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21179
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Enhancing Underwater Light Field Images via Global Geometry-aware Diffusion Process
Lin, Yuji
Zhao, Qian
Yue, Zongsheng
Hou, Junhui
Meng, Deyu
Computer Vision and Pattern Recognition
This work studies the challenging problem of acquiring high-quality underwater images via 4-D light field (LF) imaging. To this end, we propose GeoDiff-LF, a novel diffusion-based framework built upon SD-Turbo to enhance underwater 4-D LF imaging by leveraging its spatial-angular structure. GeoDiff-LF consists of three key adaptations: (1) a modified U-Net architecture with convolutional and attention adapters to model geometric cues, (2) a geometry-guided loss function using tensor decomposition and progressive weighting to regularize global structure, and (3) an optimized sampling strategy with noise prediction to improve efficiency. By integrating diffusion priors and LF geometry, GeoDiff-LF effectively mitigates color distortion in underwater scenes. Extensive experiments demonstrate that our framework outperforms existing methods across both visual fidelity and quantitative performance, advancing the state-of-the-art in enhancing underwater imaging. The code will be publicly available at https://github.com/linlos1234/GeoDiff-LF.
title Enhancing Underwater Light Field Images via Global Geometry-aware Diffusion Process
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.21179