Chenyang Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chenyang Wang has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Shengping Zhang
Harbin Institute of Technology, Harbin, China
7 shared publications - Qingming Huang
University of Chinese Academy of Sciences
4 shared publications - Zonglin Li
Harbin Institute of Technology, Weihai, China
4 shared publications - Hongxun Yao
Harbin Institute of Technology, Harbin, China
3 shared publications - Quanling Meng
School of Computer Science and Technology, Harbin Institute of Technology, Shandong, China
3 shared publications - Shunyuan Zheng
School of Computer Science and Technology, Harbin Institute of Technology, Weihai, P.R.China
3 shared publications
Latest Publications
- 28 September 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (10) , 453
G2S2-IR: Glocal Gaussian Splatting with Surface Awareness for Inverse Rendering
- 28 September 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (10) , 453
G2S2-IR: Glocal Gaussian Splatting with Surface Awareness for Inverse Rendering
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Generalizable and Relightable Gaussian Splatting for Human Novel View Synthesis
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessGeneralizable and Relightable Gaussian Splatting for Human Novel View Synthesis
- 4 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 1639-1653
D3BSR: Blind Super-Resolution via Diffusion-Based Disentangled Degradation Representation
Existing Blind Super-Resolution (BSR) methods are mostly trained on artificial synthetic degradation data pairs or rely on specific degradation priors, which lead to poor performance due to the trained degradation mismatch between other unknown complex degradations in real-world scenarios. To tackle this problem, we propose a novel Diffusion-based Disentangled Degradation representation method for BSR, dubbed D3BSR, which disentangles arbitrary unknown degradation into structure and texture degradations to enhance perception and fidelity quality individually. Specifically, the structure degradation is optimized by degradation distribution transition with a self-supervised collaborative learning strategy to recursively minimize the perception error. The texture degradation is restored through posterior sampling controlled by a fidelity coefficient to leverage rich texture priors encapsulated in a pre-trained diffusion model for preserving fidelity. The degraded image is super-resolved using an analytical solution with the pseudo inverse of the structural and texture degradation, which achieves a controllable trade-off between perception and fidelity and does not rely on any degradation priors or extra-supervised training. Extensive experiments on the nine heavily degraded synthetic and real-world natural and face datasets demonstrate that our D3BSR outperforms SOTA methods on the diverse metrics in reconstruction faithfulness and perceptual quality.
- 4 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 1639-1653
D3BSR: Blind Super-Resolution via Diffusion-Based Disentangled Degradation Representation
Existing Blind Super-Resolution (BSR) methods are mostly trained on artificial synthetic degradation data pairs or rely on specific degradation priors, which lead to poor performance due to the trained degradation mismatch between other unknown complex degradations in real-world scenarios. To tackle this problem, we propose a novel Diffusion-based Disentangled Degradation representation method for BSR, dubbed D3BSR, which disentangles arbitrary unknown degradation into structure and texture degradations to enhance perception and fidelity quality individually. Specifically, the structure degradation is optimized by degradation distribution transition with a self-supervised collaborative learning strategy to recursively minimize the perception error. The texture degradation is restored through posterior sampling controlled by a fidelity coefficient to leverage rich texture priors encapsulated in a pre-trained diffusion model for preserving fidelity. The degraded image is super-resolved using an analytical solution with the pseudo inverse of the structural and texture degradation, which achieves a controllable trade-off between perception and fidelity and does not rely on any degradation priors or extra-supervised training. Extensive experiments on the nine heavily degraded synthetic and real-world natural and face datasets demonstrate that our D3BSR outperforms SOTA methods on the diverse metrics in reconstruction faithfulness and perceptual quality.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 9733-9742
REA-Listener: Real-Time Listening Head Generation with Dynamic Emotion Modeling and Flexible Modality Adaptation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 9733-9742
Open AccessREA-Listener: Real-Time Listening Head Generation with Dynamic Emotion Modeling and Flexible Modality Adaptation
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 2593-2602
Shape-Guided Clothing Warping for Virtual Try-On
Image-based virtual try-on aims to seamlessly fit in-shop clothing to a person image while maintaining pose consistency. Existing methods commonly employ the thin plate spline (TPS) transformation or appearance flow to deform in-shop clothing for aligning with the person's body. Despite their promising performance, these methods often lack precise control over fine details, leading to inconsistencies in shape between clothing and the person's body as well as distortions in exposed limb regions. To tackle these challenges, we propose a novel shape-guided clothing warping method for virtual try-on, dubbed SCW-VTON, which incorporates global shape constraints and additional limb textures to enhance the realism and consistency of the warped clothing and try-on results. To integrate global shape constraints for clothing warping, we devise a dual-path clothing warping module comprising a shape path and a flow path. The former path captures the clothing shape aligned with the person's body, while the latter path leverages the mapping between the pre- and post-deformation of the clothing shape to guide the estimation of appearance flow. Furthermore, to alleviate distortions in limb regions of try-on results, we integrate detailed limb guidance by developing a limb reconstruction network based on masked image modeling. Through the utilization of SCW-VTON, we are able to generate try-on results with enhanced clothing shape consistency and precise control over details. Extensive experiments demonstrate the superiority of our approach over state-of-the-art methods both qualitatively and quantitatively.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 2593-2602
Open AccessShape-Guided Clothing Warping for Virtual Try-On
Image-based virtual try-on aims to seamlessly fit in-shop clothing to a person image while maintaining pose consistency. Existing methods commonly employ the thin plate spline (TPS) transformation or appearance flow to deform in-shop clothing for aligning with the person's body. Despite their promising performance, these methods often lack precise control over fine details, leading to inconsistencies in shape between clothing and the person's body as well as distortions in exposed limb regions. To tackle these challenges, we propose a novel shape-guided clothing warping method for virtual try-on, dubbed SCW-VTON, which incorporates global shape constraints and additional limb textures to enhance the realism and consistency of the warped clothing and try-on results. To integrate global shape constraints for clothing warping, we devise a dual-path clothing warping module comprising a shape path and a flow path. The former path captures the clothing shape aligned with the person's body, while the latter path leverages the mapping between the pre- and post-deformation of the clothing shape to guide the estimation of appearance flow. Furthermore, to alleviate distortions in limb regions of try-on results, we integrate detailed limb guidance by developing a limb reconstruction network based on masked image modeling. Through the utilization of SCW-VTON, we are able to generate try-on results with enhanced clothing shape consistency and precise control over details. Extensive experiments demonstrate the superiority of our approach over state-of-the-art methods both qualitatively and quantitatively.
- 7 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32 (10577149) , 4701-4715
Unsupervised Low-Light Video Enhancement With Spatial-Temporal Co-Attention Transformer
Existing low-light video enhancement methods are dominated by Convolution Neural Networks (CNNs) that are trained in a supervised manner. Due to the difficulty of collecting paired dynamic low/normal-light videos in real-world scenes, they are usually trained on synthetic, static, and uniform motion videos, which undermines their generalization to real-world scenes. Additionally, these methods typically suffer from temporal inconsistency (e.g., flickering artifacts and motion blurs) when handling large-scale motions since the local perception property of CNNs limits them to model long-range dependencies in both spatial and temporal domains. To address these problems, we propose the first unsupervised method for low-light video enhancement to our best knowledge, named LightenFormer, which models long-range intra- and inter-frame dependencies with a spatial-temporal co-attention transformer to enhance brightness while maintaining temporal consistency. Specifically, an effective but lightweight S-curve Estimation Network (SCENet) is first proposed to estimate pixel-wise S-shaped non-linear curves (S-curves) to adaptively adjust the dynamic range of an input video. Next, to model the temporal consistency of the video, we present a Spatial-Temporal Refinement Network (STRNet) to refine the enhanced video. The core module of STRNet is a novel Spatial-Temporal Co-attention Transformer (STCAT), which exploits multi-scale self- and cross-attention interactions to capture long-range correlations in both spatial and temporal domains among frames for implicit motion estimation. To achieve unsupervised training, we further propose two non-reference loss functions based on the invertibility of the S-curve and the noise independence among frames. Extensive experiments on the SDSD and LLIV-Phone datasets demonstrate that our LightenFormer outperforms state-of-the-art methods.
- 7 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32 (10577149) , 4701-4715
Unsupervised Low-Light Video Enhancement With Spatial-Temporal Co-Attention Transformer
Existing low-light video enhancement methods are dominated by Convolution Neural Networks (CNNs) that are trained in a supervised manner. Due to the difficulty of collecting paired dynamic low/normal-light videos in real-world scenes, they are usually trained on synthetic, static, and uniform motion videos, which undermines their generalization to real-world scenes. Additionally, these methods typically suffer from temporal inconsistency (e.g., flickering artifacts and motion blurs) when handling large-scale motions since the local perception property of CNNs limits them to model long-range dependencies in both spatial and temporal domains. To address these problems, we propose the first unsupervised method for low-light video enhancement to our best knowledge, named LightenFormer, which models long-range intra- and inter-frame dependencies with a spatial-temporal co-attention transformer to enhance brightness while maintaining temporal consistency. Specifically, an effective but lightweight S-curve Estimation Network (SCENet) is first proposed to estimate pixel-wise S-shaped non-linear curves (S-curves) to adaptively adjust the dynamic range of an input video. Next, to model the temporal consistency of the video, we present a Spatial-Temporal Refinement Network (STRNet) to refine the enhanced video. The core module of STRNet is a novel Spatial-Temporal Co-attention Transformer (STCAT), which exploits multi-scale self- and cross-attention interactions to capture long-range correlations in both spatial and temporal domains among frames for implicit motion estimation. To achieve unsupervised training, we further propose two non-reference loss functions based on the invertibility of the S-curve and the noise independence among frames. Extensive experiments on the SDSD and LLIV-Phone datasets demonstrate that our LightenFormer outperforms state-of-the-art methods.
- Open Access
- 30 March 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 131 (11) , 3119
Correction to: Learning Enriched Hop-Aware Correlation for Robust 3D Human Pose Estimation
- 30 March 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 131 (11) , 3119
Open AccessCorrection to: Learning Enriched Hop-Aware Correlation for Robust 3D Human Pose Estimation
- 8 March 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 131 (6) , 1566-1583
Learning Enriched Hop-Aware Correlation for Robust 3D Human Pose Estimation
- 8 March 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 131 (6) , 1566-1583
Learning Enriched Hop-Aware Correlation for Robust 3D Human Pose Estimation
- 13 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 9044-9056
Automatic Shadow Generation via Exposure Fusion
Shadow generation aims to generate a plausible shadow for the inserted foreground object in a composite image. Besides the composite image and the associated mask of the inserted foreground object, existing methods also require a mask of all background objects as well as their shadows as an auxiliary input, which is laborious in practical applications. Meanwhile, most existing methods use a linear illumination transformation to darken the shadow region, which is prone to produce unrealistic shadows especially when background illumination is complex. To address these problems, this paper proposes an automatic shadow generation method, which avoids the laborious acquisition of the background object masks while harmonizing the shadow region to achieve plausible shadow effects. Specifically, to implicitly exploit background illumination to infer the shadow shape of the inserted foreground object, we first propose a Hierarchy Attention U-Net (HAU-Net) to sequentially build global interactions between the foreground object and background across spatial and channel dimensions. Since the spatial-variant property of the shadow, we formulate shadow harmonization as an exposure fusion problem and propose an Illumination-Aware Fusion Network (IFNet), which uses an improved illumination model with a double linear transformation to produce multiple under-exposure images of the shadow region. IFNet then learns pixel-wise fusion kernels that consider the local smoothness of the shadow to fuse the composite image with these under-exposure images to generate the realistic shadow of the foreground object. Extensive experiments on the DESOBA and Shadow-AR datasets demonstrate that our method achieves state-of-the-art performance for shadow generation on both the BOS and BOS-free test images.
- 13 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 9044-9056
Automatic Shadow Generation via Exposure Fusion
Shadow generation aims to generate a plausible shadow for the inserted foreground object in a composite image. Besides the composite image and the associated mask of the inserted foreground object, existing methods also require a mask of all background objects as well as their shadows as an auxiliary input, which is laborious in practical applications. Meanwhile, most existing methods use a linear illumination transformation to darken the shadow region, which is prone to produce unrealistic shadows especially when background illumination is complex. To address these problems, this paper proposes an automatic shadow generation method, which avoids the laborious acquisition of the background object masks while harmonizing the shadow region to achieve plausible shadow effects. Specifically, to implicitly exploit background illumination to infer the shadow shape of the inserted foreground object, we first propose a Hierarchy Attention U-Net (HAU-Net) to sequentially build global interactions between the foreground object and background across spatial and channel dimensions. Since the spatial-variant property of the shadow, we formulate shadow harmonization as an exposure fusion problem and propose an Illumination-Aware Fusion Network (IFNet), which uses an improved illumination model with a double linear transformation to produce multiple under-exposure images of the shadow region. IFNet then learns pixel-wise fusion kernels that consider the local smoothness of the shadow to fuse the composite image with these under-exposure images to generate the realistic shadow of the foreground object. Extensive experiments on the DESOBA and Shadow-AR datasets demonstrate that our method achieves state-of-the-art performance for shadow generation on both the BOS and BOS-free test images.