paper-with-me

홈 › Papers

LOBSTgER-enhance: an underwater image enhancement pipeline

2026-02-05 · Andreas Mentzelopoulos, Keith Ellenbogen arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.05163

Code (0)

등록된 구현이 없습니다.

Tasks

Image Enhancement

Similar Papers 제목 키워드 기반

Fast Underwater Image Enhancement for Improved Visual Perception

2019-03-23 · Md Jahidul Islam, Youya Xia, Junaed Sattar

In this paper, we present a conditional generative adversarial network-based model for real-time underwater image enhancement. To supervise the adversarial training, we formulate an objective function that evaluates the …

Generative Adversarial NetworkImage Enhancementobject-detectionObject Detection+3

Is Underwater Image Enhancement All Object Detectors Need?

2023-11-30 · Yudong Wang, Jichang Guo, Wanru He, Huan Gao 외

Underwater object detection is a crucial and challenging problem in marine engineering and aquatic robot. The difficulty is partly because of the degradation of underwater images caused by light selective absorption and …

AllImage EnhancementObjectobject-detection+1

Perceptual underwater image enhancement with deep learning and physical priors

2020-08-21 · Long Chen, Zheheng Jiang, Lei Tong, Zhihua Liu 외

Underwater image enhancement, as a pre-processing step to improve the accuracy of the following object detection task, has drawn considerable attention in the field of underwater navigation and ocean exploration. However…

Deep LearningImage EnhancementImage Generationobject-detection+1

An Underwater Image Enhancement Benchmark Dataset and Beyond

2019-01-11 · Chongyi Li, Chunle Guo, Wenqi Ren, Runmin Cong 외

Underwater image enhancement has been attracting much attention due to its significance in marine engineering and aquatic robotics. Numerous underwater image enhancement algorithms have been proposed in the last few year…

Image EnhancementUnderwater Image Restoration

A Benchmark dataset for both underwater image enhancement and underwater object detection

2020-06-29 · Long Chen, Lei Tong, Feixiang Zhou, Zheheng Jiang 외

Underwater image enhancement is such an important vision task due to its significance in marine engineering and aquatic robot. It is usually work as a pre-processing step to improve the performance of high level vision t…

Image EnhancementImage Quality AssessmentObjectobject-detection+1