LOBSTgER-enhance: an underwater image enhancement pipeline

📅 2026-02-05
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work proposes a diffusion-based image enhancement method to address the challenges of underwater photography, including low contrast, spatial blur, and wavelength-dependent color distortion caused by light absorption and scattering. The approach uniquely integrates a physics-inspired synthetic underwater degradation pipeline with a diffusion generative model, enabling the learning of an inverse mapping of the degradation process. Trained from scratch on only approximately 2.5k high-quality images, the resulting 11-million-parameter model demonstrates exceptional perceptual fidelity and generalization capability at a resolution of 512×768, significantly improving the visual quality of underwater imagery.

Technology Category

Application Category

📝 Abstract
Underwater photography presents significant inherent challenges including reduced contrast, spatial blur, and wavelength-dependent color distortions. These effects can obscure the vibrancy of marine life and awareness photographers in particular are often challenged with heavy post-processing pipelines to correct for these distortions. We develop an image-to-image pipeline that learns to reverse underwater degradations by introducing a synthetic corruption pipeline and learning to reverse its effects with diffusion-based generation. Training and evaluation are performed on a small high-quality dataset of awareness photography images by Keith Ellenbogen. The proposed methodology achieves high perceptual consistency and strong generalization in synthesizing 512x768 images using a model of ~11M parameters after training from scratch on ~2.5k images.
Problem

Research questions and friction points this paper is trying to address.

underwater image enhancement
color distortion
contrast reduction
spatial blur
Innovation

Methods, ideas, or system contributions that make the work stand out.

underwater image enhancement
diffusion-based generation
synthetic corruption pipeline
image-to-image translation
perceptual consistency
🔎 Similar Papers
💼 Related Jobs
No related jobs found.
A
Andreas P. Mentzelopoulos
Massachusetts Institute of Technology
K
Keith Ellenbogen
Massachusetts Institute of Technology