Dual High-Order Total Variation Model for Underwater Image Restoration
Yuemei Li, Guojia Hou, Peixian Zhuang, Zhenkuan Pan
TL;DR
Underwater images suffer from color cast, haze, blur, and nonuniform illumination. The authors develop an extended underwater image formation model that introduces a local ambient illumination $L(x)$ and formulate a dual high-order variational energy $E(R,L)$ with Euler’s elastica on the reflectance $R$ and a Laplacian on $L$, enabling simultaneous restoration of color, structure, and illumination. An adaptive color correction scheme and an ADMM-based solver are integrated to efficiently estimate $R$ and $L$ from degraded images, with local illumination estimation driven by brightest-pixel intuition and a refined gamma correction. Empirical results on UIEB, UIQS, and Color-Checker7 using FADE, Entropy, UCIQE, and FDUM show state-of-the-art performance in color correction, dehazing, and detail preservation, and the method generalizes to outdoor defogging and low-light enhancement, suggesting broad practical impact for vision tasks in challenging lighting conditions.
Abstract
Underwater images are typically characterized by color cast, haze, blurring, and uneven illumination due to the selective absorption and scattering when light propagates through the water, which limits their practical applications. Underwater image enhancement and restoration (UIER) is one crucial mode to improve the visual quality of underwater images. However, most existing UIER methods concentrate on enhancing contrast and dehazing, rarely pay attention to the local illumination differences within the image caused by illumination variations, thus introducing some undesirable artifacts and unnatural color. To address this issue, an effective variational framework is proposed based on an extended underwater image formation model (UIFM). Technically, dual high-order regularizations are successfully integrated into the variational model to acquire smoothed local ambient illuminance and structure-revealed reflectance in a unified manner. In our proposed framework, the weight factors-based color compensation is combined with the color balance to compensate for the attenuated color channels and remove the color cast. In particular, the local ambient illuminance with strong robustness is acquired by performing the local patch brightest pixel estimation and an improved gamma correction. Additionally, we design an iterative optimization algorithm relying on the alternating direction method of multipliers (ADMM) to accelerate the solution of the proposed variational model. Considerable experiments on three real-world underwater image datasets demonstrate that the proposed method outperforms several state-of-the-art methods with regard to visual quality and quantitative assessments. Moreover, the proposed method can also be extended to outdoor image dehazing, low-light image enhancement, and some high-level vision tasks. The code is available at https://github.com/Hou-Guojia/UDHTV.