NeuroPump: Simultaneous Geometric and Color Rectification for Underwater Images

2024-12-20

AI Summary

Underwater imaging suffers from severe coupling between geometric distortion (caused by refraction) and color degradation (induced by absorption and scattering), making joint correction extremely challenging. To address this, we propose the first physics-inspired, self-supervised Neural Radiance Fields (NeRF) framework that explicitly decouples water-induced effects into three physically interpretable components: refraction (geometric distortion), absorption, and scattering (chromatic degradation). These are seamlessly integrated into a unified NeRF architecture for end-to-end joint optimization. We further introduce the first real-world, paired (in-air vs. underwater) 360° underwater benchmark dataset to support training and evaluation. Our method enables simultaneous water-removal reconstruction, novel-view synthesis, and optical parameter control. Quantitatively, it achieves significant improvements over state-of-the-art methods in PSNR, SSIM, and LPIPS; qualitatively, it yields more natural and robust visual results.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Machine Learning: Unsupervised & Self-Supervised Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Underwater image restoration aims to remove geometric and color distortions due to water refraction, absorption and scattering. Previous studies focus on restoring either color or the geometry, but to our best knowledge, not both. However, in practice it may be cumbersome to address the two rectifications one-by-one. In this paper, we propose NeuroPump, a self-supervised method to simultaneously optimize and rectify underwater geometry and color as if water were pumped out. The key idea is to explicitly model refraction, absorption and scattering in Neural Radiance Field (NeRF) pipeline, such that it not only performs simultaneous geometric and color rectification, but also enables to synthesize novel views and optical effects by controlling the decoupled parameters. In addition, to address issue of lack of real paired ground truth images, we propose an underwater 360 benchmark dataset that has real paired (i.e., with and without water) images. Our method clearly outperforms other baselines both quantitatively and qualitatively. Our project page is available at: https://ygswu.github.io/NeuroPump.github.io/.

Problem

• Underwater Photography
• Color Correction
• Shape Distortion

Innovation

• Neural Radiance Fields
• Simultaneous Shape and Color Restoration
• Underwater Image Enhancement