22 papers
LoopMoEVR: Loop-Based Degradation-Aware Mixture-of-Experts for Unified UHD Video Restoration
Yucheng Xin, Runci Bai, Yongcong Wang +5
Recently, unified high-definition image restoration has attracted considerable attention; however, existing models tend to excessively increase their depth in pursuit of improved g…
LoopLUT: 3D Lookup Tables with Progressive Region Refinement for Real-Time 4K Image Enhancement
Yang Ye, Jiajun Ma, Chen Wu +5
Color enhancement of 4K images must meet a quality target under a tight compute budget. Three-dimensional lookup tables (3D LUTs) dominate real-time enhancement because they decide…
Loop-Mamba: A Loop Mamba with Degradation-Aware and Shared Memory for Old Photo Restoration
Runci Bai, Yucheng Xin, Pu Wang +8
Old photographs often suffer from multiple coupled degradations, including scratches, cracks, fading, blur, noise, and missing regions, severely degrading both visual quality and s…
LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing
Yongcong Wang, Chengchao Shen, Guangwei Gao +5
Currently, there is a gap in the field of ultra-high-definition (UHD) video dehazing due to the lack of a benchmark for evaluation. Furthermore, existing video dehazing methods can…
RPBA-Net: An Interpretable Residual Pyramid Bilateral Affine Network for RAW-Domain ISP Enhancement
Yucheng Xin, Wu Chen, Xiang Chen +7
To address module fragmentation, uninterpretable mappings, and deployment constraints in RAW-domain demosaicing, color correction, and detail enhancement, this paper proposes RPBA-…
6thGrid-Net: Unified Remote Sensing Image Dehazing Based on Color Restoration and Edge-Preserving
Runci Bai, Kui Jiang, Xiang Chen +4
Remote sensing images are frequently degraded by adverse weather conditions, particularly clouds and haze, which severely impair downstream applications. Existing restoration metho…
UHD-GPGNet: UHD Video Denoising via Gaussian-Process-Guided Local Spatio-Temporal Modeling
Weiyuan He, Chen Wu, Pengwen Dai +6
Ultra-high-definition (UHD) video denoising requires simultaneously suppressing complex spatio-temporal degradations, preserving fine textures and chromatic stability, and maintain…
UHD Low-Light Image Enhancement via Real-Time Enhancement Methods with Clifford Information Fusion
Xiaohan Wang, Chen Wu, Dawei Zhao +8
Considering efficiency, ultra-high-definition (UHD) low-light image restoration is extremely challenging. Existing methods based on Transformer architectures or high-dimensional co…
Unifying VLM-Guided Flow Matching and Spectral Anomaly Detection for Interpretable Veterinary Diagnosis
Pu Wang, Zhixuan Mao, Jialu Li +3
Automatic diagnosis of canine pneumothorax is challenged by data scarcity and the need for trustworthy models. To address this, we first introduce a public, pixel-level annotated d…
UHD Image Deblurring via Autoregressive Flow with Ill-conditioned Constraints
Yucheng Xin, Dawei Zhao, Xiang Chen +6
Ultra-high-definition (UHD) image deblurring poses significant challenges for UHD restoration methods, which must balance fine-grained detail recovery and practical inference effic…
Teacher-Guided Causal Interventions for Image Denoising: Orthogonal Content-Noise Disentanglement in Vision Transformers
Kuai Jiang, Zhaoyan Ding, Guijuan Zhang +2
Conventional image denoising models often inadvertently learn spurious correlations between environmental factors and noise patterns. Moreover, due to high-frequency ambiguity, the…
SSPFormer: Self-Supervised Pretrained Transformer for MRI Images
Jingkai Li, Xiaoze Tian, Yuhang Shen +4
The pre-trained transformer demonstrates remarkable generalization ability in natural image processing. However, directly transferring it to magnetic resonance images faces two key…
DCA-LUT: Deep Chromatic Alignment with 5D LUT for Purple Fringing Removal
Jialang Lu, Shuning Sun, Pu Wang +6
Purple fringing, a persistent artifact caused by Longitudinal Chromatic Aberration (LCA) in camera lenses, has long degraded the clarity and realism of digital imaging. Traditional…
4KDehazeFlow: Ultra-High-Definition Image Dehazing via Flow Matching
Xingchi Chen, Pu Wang, Xuerui Li +7
Ultra-High-Definition (UHD) image dehazing faces challenges such as limited scene adaptability in prior-based methods and high computational complexity with color distortion in dee…
CAST-LUT: Tokenizer-Guided HSV Look-Up Tables for Purple Flare Removal
Pu Wang, Shuning Sun, Jialang Lu +7
Purple flare, a diffuse chromatic aberration artifact commonly found around highlight areas, severely degrades the tone transition and color of the image. Existing traditional meth…
Foggy Crowd Counting: Combining Physical Priors and KAN-Graph
Yuhao Wang, Zhuoran Zheng, Han Hu +3
Aiming at the key challenges of crowd counting in foggy environments, such as long-range target blurring, local feature degradation, and image contrast attenuation, this paper prop…
Hazy Pedestrian Trajectory Prediction via Physical Priors and Graph-Mamba
Jian Chen, Zhuoran Zheng, Han Hu +4
To address the issues of physical information degradation and ineffective pedestrian interaction modeling in pedestrian trajectory prediction under hazy weather conditions, we prop…
FlowLUT: Efficient Image Enhancement via Differentiable LUTs and Iterative Flow Matching
Liubing Hu, Chen Wu, Anrui Wang +3
Deep learning-based image enhancement methods face a fundamental trade-off between computational efficiency and representational capacity. For example, although a conventional thre…
DeLiVR: Differential Spatiotemporal Lie Bias for Efficient Video Deraining
Shuning Sun, Jialang Lu, Xiang Chen +5
Videos captured in the wild often suffer from rain streaks, blur, and noise. In addition, even slight changes in camera pose can amplify cross-frame mismatches and temporal artifac…
UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache
Pu Wang, Pengwen Dai, Chen Wu +5
In this paper, we propose an efficient visual transformer framework for ultra-high-definition (UHD) image dehazing that addresses the key challenges of slow training speed and high…
UniFlowRestore: A General Video Restoration Framework via Flow Matching and Prompt Guidance
Shuning Sun, Yu Zhang, Chen Wu +4
Video imaging is often affected by complex degradations such as blur, noise, and compression artifacts. Traditional restoration methods follow a "single-task single-model" paradigm…
Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restoration
Chen Wu, Ling Wang, Long Peng +2
With the popularization of high-end mobile devices, Ultra-high-definition (UHD) images have become ubiquitous in our lives. The restoration of UHD images is a highly challenging pr…