papers

Publications (47)

cs.CV2026

Bird-SR: Bidirectional Reward-Guided Diffusion for Real-World Image Super-Resolution

Zihao Fan, Xin Lu, Yidi Liu +4

Powered by multimodal text-to-image priors, diffusion-based super-resolution excels at synthesizing intricate details; however, models trained on synthetic low-resolution (LR) and…

cs.CV2026

CompEvent: Complex-valued Event-RGB Fusion for Low-light Video Enhancement and Deblurring

Mingchen Zhong, Xin Lu, Dong Li +4

Low-light video deblurring poses significant challenges in applications like nighttime surveillance and autonomous driving due to dim lighting and long exposures. While event camer…

cs.CV2025

Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning

Kunyu Wang, Xueyang Fu, Xin Lu +4

Continual test-time adaptive object detection (CTTA-OD) aims to online adapt a source pre-trained detector to ever-changing environments during inference under continuous domain sh…

cs.CV2026

IR-Flow: Bridging Discriminative and Generative Image Restoration via Rectified Flow

Zihao Fan, Xin Lu, Jie Xiao +3

In image restoration, single-step discriminative mappings often lack fine details via expectation learning, whereas generative paradigms suffer from inefficient multi-step sampling…

cs.CV2024

Rethinking Real-world Image Deraining via An Unpaired Degradation-Conditioned Diffusion Model

Yiyang Shen, Mingqiang Wei, Yongzhen Wang +2

Recent diffusion models have exhibited great potential in generative modeling tasks. Part of their success can be attributed to the ability of training stable on huge sets of paire…

cs.CV2025

NTIRE 2025 Image Shadow Removal Challenge Report

Florin-Alexandru Vasluianu, Tim Seizinger, Zhuyun Zhou +79

This work examines the findings of the NTIRE 2025 Shadow Removal Challenge. A total of 306 participants have registered, with 17 teams successfully submitting their solutions durin…

cs.CV2023

CCM: Adding Conditional Controls to Text-to-Image Consistency Models

Jie Xiao, Kai Zhu, Han Zhang +5

Consistency Models (CMs) have showed a promise in creating visual content efficiently and with high quality. However, the way to add new conditional controls to the pretrained CMs…

cs.CV2026

Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Dataset

Senyan Xu, Zhijing Sun, Kean Liu +5

Event-based low-light image enhancement (LIE) methods mainly focus on incorporating high dynamic range (HDR) information from events while overlooking the essential global illumina…

eess.IV2020

Noise2Blur: Online Noise Extraction and Denoising

Huangxing Lin, Weihong Zeng, Xinghao Ding +3

We propose a new framework called Noise2Blur (N2B) for training robust image denoising models without pre-collected paired noisy/clean images. The training of the model requires on…

cs.CL2026

Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models

Yawen Shao, Jie Xiao, Kai Zhu +6

Reinforcement learning (RL) holds immense promise for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, progress is fundamentally constraine…

cs.CV2023

Revisiting Single Image Reflection Removal In the Wild

Yurui Zhu, Xueyang Fu, Peng-Tao Jiang +5

This research focuses on the issue of single-image reflection removal (SIRR) in real-world conditions, examining it from two angles: the collection pipeline of real reflection pair…

cs.CV2018

A^2Net: Adjacent Aggregation Networks for Image Raindrop Removal

Huangxing Lin, Xueyang Fu, Changxing Jing +2

Existing methods for single images raindrop removal either have poor robustness or suffer from parameter burdens. In this paper, we propose a new Adjacent Aggregation Network (A^2N…

cs.CV2021

Twice Mixing: A Rank Learning based Quality Assessment Approach for Underwater Image Enhancement

Zhenqi Fu, Xueyang Fu, Yue Huang +1

To improve the quality of underwater images, various kinds of underwater image enhancement (UIE) operators have been proposed during the past few years. However, the lack of effect…

cs.CV2026

FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution

Yidi Liu, Zihao Fan, Jie Huang +6

Reinforcement Learning with Human Feedback (RLHF) has proven effective in image generation field guided by reward models to align human preferences. Motivated by this, adapting RLH…

cs.CV2026

EventGait: Towards Robust Gait Recognition with Event Streams

Senyan Xu, Shuai Chen, Chuanfu Shen +4

Gait recognition enables non-intrusive, privacy-preserving identification but suffers in uncontrolled environments due to illumination and motion sensitivity of conventional camera…

cs.CV2025

PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation

Kunyu Wang, Xueyang Fu, Yuanfei Bao +4

Continual Test-Time Adaptation (CTTA) aims to online adapt a pre-trained model to changing environments during inference. Most existing methods focus on exploiting target data, whi…

cs.CV2020

Real-world Person Re-Identification via Degradation Invariance Learning

Yukun Huang, Zheng-Jun Zha, Xueyang Fu +2

Person re-identification (Re-ID) in real-world scenarios usually suffers from various degradation factors, e.g., low-resolution, weak illumination, blurring and adverse weather. On…

cs.CV2018

A Deep Tree-Structured Fusion Model for Single Image Deraining

Xueyang Fu, Qi Qi, Yue Huang +3

We propose a simple yet effective deep tree-structured fusion model based on feature aggregation for the deraining problem. We argue that by effectively aggregating features, a rel…

cs.CV2025

Elucidating and Endowing the Diffusion Training Paradigm for General Image Restoration

Xin Lu, Xueyang Fu, Jie Xiao +3

While diffusion models demonstrate strong generative capabilities in image restoration (IR) tasks, their complex architectures and iterative processes limit their practical applica…

cs.CV2018

Lightweight Pyramid Networks for Image Deraining

Xueyang Fu, Borong Liang, Yue Huang +2

Existing deep convolutional neural networks have found major success in image deraining, but at the expense of an enormous number of parameters. This limits their potential applica…

cs.CV2026

OmniVR: Joint Video-Audio Conditional Generation for Restoring Degraded Historical Films

Xin Lu, Zihao Fan, Mingchen Zhong +3

Historical films suffer from co-occurring visual and audio degradations---blur, noise, flicker, hiss, clipping, and dropout---yet existing methods restore each modality independent…

cs.CV2025

Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement

Yidi Liu, Xueyang Fu, Jie Huang +5

Ultra-High Definition (UHD) image restoration faces a trade-off between computational efficiency and high-frequency detail retention. While Variational Autoencoders (VAEs) improve…

eess.IV2024

Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolution

Long Peng, Yang Cao, Renjing Pei +5

Real-SR endeavors to produce high-resolution images with rich details while mitigating the impact of multiple degradation factors. Although existing methods have achieved impressiv…

cs.CV2025

SCott: Accelerating Diffusion Models with Stochastic Consistency Distillation

Hongjian Liu, Qingsong Xie, TianXiang Ye +6

The iterative sampling procedure employed by diffusion models (DMs) often leads to significant inference latency. To address this, we propose Stochastic Consistency Distillation (S…

cs.CV2023

Decoupling Degradation and Content Processing for Adverse Weather Image Restoration

Xi Wang, Xueyang Fu, Peng-Tao Jiang +4

Adverse weather image restoration strives to recover clear images from those affected by various weather types, such as rain, haze, and snow. Each weather type calls for a tailored…

cs.CV2025

Decouple to Reconstruct: High Quality UHD Restoration via Active Feature Disentanglement and Reversible Fusion

Yidi Liu, Dong Li, Yuxin Ma +4

Ultra-high-definition (UHD) image restoration often faces computational bottlenecks and information loss due to its extremely high resolution. Existing studies based on Variational…

cs.CV2025

Towards Better De-raining Generalization via Rainy Characteristics Memorization and Replay

Kunyu Wang, Xueyang Fu, Chengzhi Cao +3

Current image de-raining methods primarily learn from a limited dataset, leading to inadequate performance in varied real-world rainy conditions. To tackle this, we introduce a new…

cs.CV2018

Residual-Guide Feature Fusion Network for Single Image Deraining

Zhiwen Fan, Huafeng Wu, Xueyang Fu +2

Single image rain streaks removal is extremely important since rainy images adversely affect many computer vision systems. Deep learning based methods have found great success in i…

cs.CV2025

AIM 2025 Challenge on High FPS Motion Deblurring: Methods and Results

George Ciubotariu, Florin-Alexandru Vasluianu, Zhuyun Zhou +44

This paper presents a comprehensive review of the AIM 2025 High FPS Non-Uniform Motion Deblurring Challenge, highlighting the proposed solutions and final results. The objective of…

cs.CV2026

The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview

Jiatong Li, Zheng Chen, Kai Liu +91

This paper provides a review of the NTIRE 2026 challenge on mobile real-world image super-resolution, highlighting the proposed solutions and the resulting outcomes. The challenge…

cs.CV2025

RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions

Anran Wu, Long Peng, Xin Di +6

Feedforward 3D Gaussian Splatting (3DGS) overcomes the limitations of optimization-based 3DGS by enabling fast and high-quality reconstruction without the need for per-scene optimi…

cs.CV2025

NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results

Lei Sun, Andrea Alfarano, Peiqi Duan +85

This paper presents an overview of NTIRE 2025 the First Challenge on Event-Based Image Deblurring, detailing the proposed methodologies and corresponding results. The primary goal…

cs.CV2025

VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs

Jiaying Zhu, Yurui Zhu, Xin Lu +5

Multimodal Large Language Models (MLLMs) encounter significant computational and memory bottlenecks from the massive number of visual tokens generated by high-resolution images or…

eess.IV2025

NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolution

Marcos V. Conde, Radu Timofte, Zihao Lu +36

This paper reviews the NTIRE 2025 RAW Image Restoration and Super-Resolution Challenge, highlighting the proposed solutions and results. New methods for RAW Restoration and Super-R…

cs.CV2024

FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining

Dong Li, Yidi Liu, Xueyang Fu +2

Image deraining aims to remove rain streaks from rainy images and restore clear backgrounds. Currently, some research that employs the Fourier transform has proved to be effective…

eess.IV2024

MIPI 2024 Challenge on Demosaic for HybridEVS Camera: Methods and Results

Yaqi Wu, Zhihao Fan, Xiaofeng Chu +46

The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algor…

cs.CV2026

Iterative Inference-time Scaling with Adaptive Frequency Steering for Image Super-Resolution

Hexin Zhang, Dong Li, Jie Huang +3

Diffusion models have become a leading paradigm for image super-resolution (SR), but existing methods struggle to guarantee both the high-frequency perceptual quality and the low-f…

cs.CV2025

Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restoration

Long Peng, Xin Di, Zhanfeng Feng +6

Image restoration aims to recover details and enhance contrast in degraded images. With the growing demand for high-quality imaging (\textit{e.g.}, 4K and 8K), achieving a balance…

cs.NE2026

Fractional-order Spiking Neural Network

Chengjie Ge, Yufeng Peng, Zihao Li +6

Spiking Neural Networks (SNNs) draw inspiration from biological neurons to enable brain-like computation, demonstrating effectiveness in processing temporal information with energy…

cs.CV2025

EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction

Chengjie Ge, Xueyang Fu, Peng He +3

Leveraging its robust linear global modeling capability, Mamba has notably excelled in computer vision. Despite its success, existing Mamba-based vision models have overlooked the…

cs.CV2014

Bayesian Nonparametric Dictionary Learning for Compressed Sensing MRI

Yue Huang, John Paisley, Qin Lin +3

We develop a Bayesian nonparametric model for reconstructing magnetic resonance images (MRI) from highly undersampled k-space data. We perform dictionary learning as part of the im…

cs.CV2025

AIM 2025 challenge on Inverse Tone Mapping Report: Methods and Results

Chao Wang, Francesco Banterle, Bin Ren +25

This paper presents a comprehensive review of the AIM 2025 Challenge on Inverse Tone Mapping (ITM). The challenge aimed to push forward the development of effective ITM algorithms…

cs.CV2025

AIM 2025 Low-light RAW Video Denoising Challenge: Dataset, Methods and Results

Alexander Yakovenko, George Chakvetadze, Ilya Khrapov +17

This paper reviews the AIM 2025 (Advances in Image Manipulation) Low-Light RAW Video Denoising Challenge. The task is to develop methods that denoise low-light RAW video by exploit…

cs.CV2024

DemosaicFormer: Coarse-to-Fine Demosaicing Network for HybridEVS Camera

Senyan Xu, Zhijing Sun, Jiaying Zhu +3

Hybrid Event-Based Vision Sensor (HybridEVS) is a novel sensor integrating traditional frame-based and event-based sensors, offering substantial benefits for applications requiring…

cs.CV2017

Clearing the Skies: A deep network architecture for single-image rain removal

Xueyang Fu, Jiabin Huang, Xinghao Ding +2

We introduce a deep network architecture called DerainNet for removing rain streaks from an image. Based on the deep convolutional neural network (CNN), we directly learn the mappi…

cs.CV2021

Unfolding Taylor's Approximations for Image Restoration

Man Zhou, Zeyu Xiao, Xueyang Fu +3

Deep learning provides a new avenue for image restoration, which demands a delicate balance between fine-grained details and high-level contextualized information during recovering…

cs.CV2026

GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting

Mingyu Shi, Xin Di, Long Peng +8

Continuous Spatio-Temporal Video Super-Resolution (C-STVSR) aims to simultaneously enhance the spatial resolution and frame rate of videos by arbitrary scale factors, offering grea…