1 citations · 4 across the 19 of their papers we have counts for
20 papers
EvoGS: Modeling Deformation Evolution for Dynamic Gaussian Splatting
Wei Dong, Shahram Shirani, Jun Chen +1
Recent extensions of 3D Gaussian Splatting (3DGS) enable real-time novel view synthesis in dynamic scenes by learning time-conditioned Gaussian deformations. However, existing MLP-…
Low Light Image Enhancement Challenge at NTIRE 2026
George Ciubotariu, Sharif S M A, Abdur Rehman +90
This paper presents a comprehensive review of the NTIRE 2026 Low Light Image Enhancement Challenge, highlighting the proposed solutions and final results. The objective of this cha…
PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
Wei Dong, Han Zhou, Terry Ji +6
Adverse weather removal (AWR) in real-world images remains challenging due to heterogeneous and unseen degradations, while distortion-driven training often yields overly smooth res…
NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
Xin Li, Yeying Jin, Suhang Yao +95
This paper presents an overview of the NTIRE 2026 Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images. Building upon the success of the first edition, this c…
RealDiffusion: Physics-informed Attention for Multi-character Storybook Generation
Qi Zhao, Jun Chen, Ivor Tsang +1
While modern diffusion models excel at generating diverse single images, extending this to sequential generation reveals a fundamental challenge: balancing narrative dynamism with…
UniBlendNet: Unified Global, Multi-Scale, and Region-Adaptive Modeling for Ambient Lighting Normalization
Jiatao Dai, Wei Dong, Han Zhou +2
Ambient Lighting Normalization (ALN) aims to restore images degraded by complex, spatially varying illumination conditions. Existing methods, such as IFBlend, leverage frequency-do…
RetinexDualV2: Physically-Grounded Dual Retinex for Generalized UHD Image Restoration
Mohab Kishawy, Jun Chen
We propose RetinexDualV2, a unified, physically grounded dual-branch framework for diverse Ultra-High-Definition (UHD) image restoration. Unlike generic models, our method employs…
HistoFusionNet: Histogram-Guided Fusion and Frequency-Adaptive Refinement for Nighttime Image Dehazing
Mohammad Heydari, Wei Dong, Shahram Shirani +2
Nighttime image dehazing remains a challenging low-level vision problem due to the joint presence of haze, glow, non-uniform illumination, color distortion, and sensor noise, which…
Zero-Reference Joint Low-Light Enhancement and Deblurring via Visual Autoregressive Modeling with VLM-Derived Modulation
Wei Dong, Han Zhou, Junwei Lin +1
Real-world dark images commonly exhibit not only low visibility and contrast but also complex noise and blur, posing significant restoration challenges. Existing methods often rely…
AU-IQA: A Benchmark Dataset for Perceptual Quality Assessment of AI-Enhanced User-Generated Content
Shushi Wang, Chunyi Li, Zicheng Zhang +5
AI-based image enhancement techniques have been widely adopted in various visual applications, significantly improving the perceptual quality of user-generated content (UGC). Howev…
Retinex-guided Histogram Transformer for Mask-free Shadow Removal
Wei Dong, Han Zhou, Seyed Amirreza Mousavi +1
While deep learning methods have achieved notable progress in shadow removal, many existing approaches rely on shadow masks that are difficult to obtain, limiting their generalizat…
Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design
Wei Dong, Yan Min, Han Zhou +1
Current Low-light Image Enhancement (LLIE) techniques predominantly rely on either direct Low-Light (LL) to Normal-Light (NL) mappings or guidance from semantic features or illumin…
LITA-GS: Illumination-Agnostic Novel View Synthesis via Reference-Free 3D Gaussian Splatting and Physical Priors
Han Zhou, Wei Dong, Jun Chen
Directly employing 3D Gaussian Splatting (3DGS) on images with adverse illumination conditions exhibits considerable difficulty in achieving high-quality, normally-exposed represen…
Constrained Gaussian Wasserstein Optimal Transport with Commutative Covariance Matrices
Jun Chen, Jia Wang, Ruibin Li +4
Optimal transport has found widespread applications in signal processing and machine learning. Among its many equivalent formulations, optimal transport seeks to reconstruct a rand…
Low-Light Image Enhancement via Generative Perceptual Priors
Han Zhou, Wei Dong, Xiaohong Liu +3
Although significant progress has been made in enhancing visibility, retrieving texture details, and mitigating noise in Low-Light (LL) images, the challenge persists in applying c…
ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction
Wei Dong, Han Zhou, Yulun Zhang +2
Exposure Correction (EC) aims to recover proper exposure conditions for images captured under over-exposure or under-exposure scenarios. While existing deep learning models have sh…
GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval
Han Zhou, Wei Dong, Xiaohong Liu +4
Most existing Low-light Image Enhancement (LLIE) methods either directly map Low-Light (LL) to Normal-Light (NL) images or use semantic or illumination maps as guides. However, the…
ShadowRefiner: Towards Mask-free Shadow Removal via Fast Fourier Transformer
Wei Dong, Han Zhou, Yuqiong Tian +4
Shadow-affected images often exhibit pronounced spatial discrepancies in color and illumination, consequently degrading various vision applications including object detection and s…
DehazeDCT: Towards Effective Non-Homogeneous Dehazing via Deformable Convolutional Transformer
Wei Dong, Han Zhou, Ruiyi Wang +3
Image dehazing, a pivotal task in low-level vision, aims to restore the visibility and detail from hazy images. Many deep learning methods with powerful representation learning cap…
Breaking Through the Haze: An Advanced Non-Homogeneous Dehazing Method based on Fast Fourier Convolution and ConvNeXt
Han Zhou, Wei Dong, Yangyi Liu +1
Haze usually leads to deteriorated images with low contrast, color shift and structural distortion. We observe that many deep learning based models exhibit exceptional performance…