The paper introduces FReSH-IR, a lightweight all-in-one weather restoration method that decomposes feature representations into high- and low-frequency components across a hierarchical encoder-decoder. By integrating spectral decomposition with Fourier-based skip connections, it captures complementary frequency information while preserving spatial detail. The approach achieves comparable restoration quality to transformer-based models while using 80% fewer parameters and operations, making it efficient for high-resolution images and constrained-resource systems.
arXiv:2406. 07435v2 Announce Type: replace-cross Abstract: Image restoration networks are usually comprised of an encoder and a decoder, responsible for aggregating image content from noisy, distorted data and to restore clean, undistorted images, respectively.
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.
arXiv:2610.29108v1 Announce Type: new Abstract: Blind all-in-one image restoration must adapt a shared model to heterogeneous and sometimes mixed degradations without a task label at test time. We in...
arXiv:2511. 10806v1 Announce Type: cross Abstract: Image deblurring is vital in computer vision, aiming to recover sharp images from blurry ones caused by motion or camera shake.
The paper introduces TSGPD-IR, a network that disentangles weather-induced artifacts from true thermal signals in infrared images. It uses weather semantics and regional degradation severity to generate adaptive prompts, estimate severity without manual labels, and select appropriate expert modules for restoration. This approach aims to reduce artifacts and preserve weak thermal details across varying weather conditions.
arXiv:2607. 05292v1 Announce Type: cross Abstract: Super-resolving coarse atmospheric fields to local PM$_{2.
The paper presents an all-in-one framework for restoring polarization images affected by multiple coupled degradations. It identifies the normalized Stokes representation as effective for separating intensity and polarization, and introduces a dual-branch architecture that uses pretrained general restoration priors for the intensity branch while transferring knowledge to the polarization branch via cross-domain feature transform. A composite-degradation benchmark is also established to support future research.
arXiv:2606. 08324v1 Announce Type: cross Abstract: Passive long-wave infrared (LWIR) hyperspectral imaging under a standoff geometry depends on atmospheric absorption and emission, as well as reflected radiance, thus making atmospheric compensation essential to get knowledge of a target of interest.
The paper introduces UAR-Net, a weather‑specific all‑in‑one restoration framework that tackles spatially heterogeneous degradations in adverse weather. It combines Gated Dual‑scale Transformer Blocks for selective global and local modeling, a Balanced Multi‑scale Skip Connection for feature integration, and an Uncertainty‑Aware Refinement Head that removes artifacts, enhances detail, and estimates predictive uncertainty. The network is trained with a Brightness‑Aware Energy Loss and achieves state‑of‑the‑art results on multiple adverse‑weather benchmarks.
Existing object detection methods predominantly utilize sRGB inputs, which are compressed from RAW sensor data using Image Signal Processors (ISP) originally designed for visualization purposes. Compared to RGB images, RAW images possess favorable noise characteristics and richer information representation, which are crucial for object detection, particularly under challenging conditions such as adverse weather or low-light environments.
arXiv:2606. 02661v1 Announce Type: cross Abstract: Accurate precipitation nowcasting is vital for disaster mitigation, but deep learning methods face a key trade-off: regression models produce over-smoothed, spectrally decaying predictions that blur convective details and violate turbulence power laws; diffusion models generate realistic yet unanchored hallucinations lacking physical grounding.
Remote sensing images acquired by unmanned aerial vehicles (UAVs) and satellites are often degraded by adverse weather, illumination variation, and imaging artifacts, which may co-occur and jointly induce global distribution shifts and local structural corruption. Although All-in-One image restoration offers an appealing unified alternative to task-specific pipelines, existing methods still suffer from weak or implicit degradation cues and parameter redundancy caused by full-rank multi-expert designs with overlapping restoration behaviors.