13 papers
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…
Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration
Chen Wu, Ling Wang, Zhuoran Zheng +6
Ultra-High-Definition (UHD) image restoration is trapped in a scalability crisis: existing models, bound to pixel-wise operations, demand unsustainable computation. While state spa…
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…
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…
Latent label distribution grid representation for modeling uncertainty
ShuNing Sun, YinSong Xiong, Yu Zhang +1
Although \textbf{L}abel \textbf{D}istribution \textbf{L}earning (LDL) has promising representation capabilities for characterizing the polysemy of an instance, the complexity and h…
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…
AdaQual-Diff: Diffusion-Based Image Restoration via Adaptive Quality Prompting
Xin Su, Chen Wu, Yu Zhang +2
Restoring images afflicted by complex real-world degradations remains challenging, as conventional methods often fail to adapt to the unique mixture and severity of artifacts prese…
AgentPolyp: Accurate Polyp Segmentation via Image Enhancement Agent
Pu Wang, Zhihua Zhang, Dianjie Lu +3
Since human and environmental factors interfere, captured polyp images usually suffer from issues such as dim lighting, blur, and overexposure, which pose challenges for downstream…
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…
UAKNN: Label Distribution Learning via Uncertainty-Aware KNN
Pu Wang, Yu Zhang, Zhuoran Zheng
Label Distribution Learning (LDL) aims to characterize the polysemy of an instance by building a set of descriptive degrees corresponding to the instance. In recent years, research…
PolypFlow: Reinforcing Polyp Segmentation with Flow-Driven Dynamics
Pu Wang, Huaizhi Ma, Zhihua Zhang +1
Accurate polyp segmentation remains challenging due to irregular lesion morphologies, ambiguous boundaries, and heterogeneous imaging conditions. While U-Net variants excel at loca…