arXiv:2608.00137v3 Announce Type: replace-cross Abstract: Underwater image enhancement (UIE) aims to recover clear images from observations affected by wavelength-dependent absorption, scattering, an...
The paper introduces a unified training framework for underwater image enhancement that addresses the scarcity of paired clean-degraded datasets. It employs a text-guided diffusion model to generate diverse, semantically consistent degraded images and uses a progressive degradation curriculum to balance learning across multiple attributes and difficulty levels. The approach also incorporates a transmission-guided one-step diffusion model to handle varying degradation severity, achieving superior performance on several underwater benchmarks.
The paper introduces 3D-USE, a two‑stage framework for underwater scene‑level enhancement that learns a persistent, visibility‑enhanced 3D representation from degraded multi‑view observations. First, the Medium Radial Basis Anchor Representation (MediumRBF) builds a medium‑aware Gaussian scene by separating object and medium effects. Then, Appearance Transition Consensus (ATC) transfers 2D underwater image enhancement knowledge into scene‑global and Gaussian‑local targets, which are realized by an Underwater Bilateral Appearance Field (U‑BAF) to render enhanced novel views without a 2D UIE model at inference. Experiments on real underwater scenes demonstrate improved visibility, cross‑view consistency, and preserved reconstruction quality.
Learning-based stereo matching models struggle in underwater environments due to scarce in-domain data and the difficulty of extracting discriminative correspondences from degraded imagery. In this work, we present $\textbf{AquaStereo}$, a perception-enhanced framework with a data simulation pipeline and a self-distillation strategy that jointly address data scarcity and feature degradation in underwater stereo matching.
The paper introduces SASC-USOD, a framework for underwater salient object detection that learns spatially adaptive coordination between two structural representations: a boundary-sensitive representation using Laplacian filtering and a region-coherent representation via dual-range anisotropic large-kernel aggregation. A spatial coordination module estimates the relative reliability of these representations and adaptively blends them based on image content. Experiments on USOD10K and USOD benchmarks show that SASC-USOD outperforms existing methods, reducing MAE by 4.07% and 23.53% respectively, and its lightweight variant achieves 21 FPS on an NVIDIA Jetson TX2 NX.
AQUA-Net is a lightweight underwater image enhancement model that fuses spatial, frequency, and illumination information through a residual encoder‑decoder architecture with dual auxiliary branches. The frequency fusion encoder incorporates Fourier‑domain cues to preserve textures and details, while the illumination‑aware decoder applies adaptive exposure correction based on a learned illumination map. Experiments on benchmark datasets and a new high‑resolution Mediterranean Sea video set demonstrate that AQUA-Net achieves state‑of‑the‑art performance with fewer parameters, showing strong generalization and robustness for real‑world underwater imaging.
arXiv:2606.06176v3 Announce Type: replace Abstract: Underwater Image Enhancement (UIE) is essential for mitigating degradations caused by water medium. Although learning-based methods have advanced s...
arXiv:2605. 13258v2 Announce Type: replace-cross Abstract: In this work, we present our winning solution for the 8th UG2+ Challenge (CVPR 2026) Track 1: Image Restoration under All-weather Conditions.
arXiv:2608.28517v1 Announce Type: new Abstract: Cross-modal image translation in remote sensing must preserve source-observed content while matching the target-domain distribution. Existing methods j...
WaterClear-GS introduces a physics-informed Gaussian splatting method tailored for underwater 3D reconstruction and appearance restoration. It models underwater degradation as intrinsic Gaussian attributes and employs a dual-branch optimization that separates clean appearance from degradation while preserving photometric consistency. The approach incorporates depth-guided geometry regularization, perception-driven supervision, exposure constraints, adaptive regularization, and spectral regularization, achieving strong novel view synthesis and image restoration performance at over 160 FPS.
Infrared-visible image fusion (IVIF) is pivotal for multimodal perception, yet reconciling the inherent information disparity between thermal and textural features remains a fundamental challenge. Existing prior-guided methods often rely on static constraints that induce optimization conflicts or utilize extrinsic semantic priors from large-scale foundation models (e.
DPSF-Net is a dual‑prior spatial‑frequency network designed for real‑world remote sensing image dehazing. It combines hazy RGB images with dark channel prior maps as joint inputs, and incorporates a spatial‑frequency residual interaction block, a prior‑guided feature attention module, and a selective kernel complementary fusion module to reduce colour shift, structural distortion, and large‑scale haze. Experiments show that DPSF-Net achieves state‑of‑the‑art performance on the RRSHID benchmark while maintaining a favorable balance of restoration quality, parameter count, and computational complexity.