Yang Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yang Zhou has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
Hui Huang
Guangdong Provincial Key Laboratory of Visual Media and Multidimensional. Intelligence, CSSE, Shenzhen University, Shenzhen, China
5 shared publications- Hui Huang
Shenzhen University, Shenzhen, China
5 shared publications Xinwei He
3 shared publications- Chunjin Song
Shenzhen University
2 shared publications - Dani Lischinski
The Hebrew University of Jerusalem
2 shared publications Daniel Cohen-Or
Shenzhen University and Tel Aviv University
2 shared publications
Latest Publications
- 11 September 2026
- Published by Springer Nature
- p. 333-350
Capacity-Controlled Multi-view Stylization of 3D Gaussian Splatting
- 11 September 2026
- Published by Springer Nature
- p. 333-350
Capacity-Controlled Multi-view Stylization of 3D Gaussian Splatting
- 26 August 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (11) , 491
PoseAlign: sculpting pose-consistent meshes via text-guided deformation
- 26 August 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (11) , 491
PoseAlign: sculpting pose-consistent meshes via text-guided deformation
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1022-1032
CLIP-AdaM: Adapting Multi-view CLIP for Open-set 3D Object Retrieval
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1022-1032
Open AccessCLIP-AdaM: Adapting Multi-view CLIP for Open-set 3D Object Retrieval
- Open Access
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1442-1451
TeDA: Boosting Vision-Lanuage Models for Zero-Shot 3D Object Retrieval via Testing-time Distribution Alignment
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1442-1451
Open AccessTeDA: Boosting Vision-Lanuage Models for Zero-Shot 3D Object Retrieval via Testing-time Distribution Alignment
- 24 April 2024
- Published by Elsevier in Computer Aided Geometric Design
- Vol. 111
Point-StyleGAN: Multi-scale point cloud synthesis with style modulation
- 24 April 2024
- Published by Elsevier in Computer Aided Geometric Design
- Vol. 111
Point-StyleGAN: Multi-scale point cloud synthesis with style modulation
- Open Access
- 26 February 2021
- Published by Association for Computing Machinery (ACM)
- p. 189-194
A Space-Frequency Adaptive Processing Method of Subband Associated Based on Focusing Transformation
Traditional space-frequency adaptive antenna array processes a broadband signal in each subband independently, which lead to amplitude and phase distortion. On the basis of establishing the traditional space-frequency adaptive antenna array model, this paper introduces an improved subband-associated space-frequency adaptive processing algorithm based on focusing transformation. This algorithm can avoid amplitude and phase distortion while suppressing interference. Simulation is performed according to the analysis and derivation process. The results completely verify the effectiveness of the improved algorithm.
- 26 February 2021
- Published by Association for Computing Machinery (ACM)
- p. 189-194
Open AccessA Space-Frequency Adaptive Processing Method of Subband Associated Based on Focusing Transformation
Traditional space-frequency adaptive antenna array processes a broadband signal in each subband independently, which lead to amplitude and phase distortion. On the basis of establishing the traditional space-frequency adaptive antenna array model, this paper introduces an improved subband-associated space-frequency adaptive processing algorithm based on focusing transformation. This algorithm can avoid amplitude and phase distortion while suppressing interference. Simulation is performed according to the analysis and derivation process. The results completely verify the effectiveness of the improved algorithm.
- Open Access
EFANet: Exchangeable Feature Alignment Network for Arbitrary Style Transfer
Style transfer has been an important topic both in computer vision and graphics. Since the seminal work of Gatys et al. first demonstrates the power of stylization through optimization in the deep feature space, quite a few approaches have achieved real-time arbitrary style transfer with straightforward statistic matching techniques. In this work, our key observation is that only considering features in the input style image for the global deep feature statistic matching or local patch swap may not always ensure a satisfactory style transfer; see e.g., Figure 1. Instead, we propose a novel transfer framework, EFANet, that aims to jointly analyze and better align exchangeable features extracted from content and style image pair. In this way, the style features from the style image seek for the best compatibility with the content information in the content image, leading to more structured stylization results. In addition, a new whitening loss is developed for purifying the computed content features and better fusion with styles in feature space. Qualitative and quantitative experiments demonstrate the advantages of our approach.
Open AccessEFANet: Exchangeable Feature Alignment Network for Arbitrary Style Transfer
Style transfer has been an important topic both in computer vision and graphics. Since the seminal work of Gatys et al. first demonstrates the power of stylization through optimization in the deep feature space, quite a few approaches have achieved real-time arbitrary style transfer with straightforward statistic matching techniques. In this work, our key observation is that only considering features in the input style image for the global deep feature statistic matching or local patch swap may not always ensure a satisfactory style transfer; see e.g., Figure 1. Instead, we propose a novel transfer framework, EFANet, that aims to jointly analyze and better align exchangeable features extracted from content and style image pair. In this way, the style features from the style image seek for the best compatibility with the content information in the content image, leading to more structured stylization results. In addition, a new whitening loss is developed for purifying the computed content features and better fusion with styles in feature space. Qualitative and quantitative experiments demonstrate the advantages of our approach.
- Open Access
ETNet: Error Transition Network for Arbitrary Style Transfer
Numerous valuable efforts have been devoted to achieving arbitrary style transfer since the seminal work of Gatys et al. However, existing state-of-the-art approaches often generate insufficiently stylized results under challenging cases. We believe a fundamental reason is that these approaches try to generate the stylized result in a single shot and hence fail to fully satisfy the constraints on semantic structures in the content images and style patterns in the style images. Inspired by the works on error-correction, instead, we propose a self-correcting model to predict what is wrong with the current stylization and refine it accordingly in an iterative manner. For each refinement, we transit the error features across both the spatial and scale domain and invert the processed features into a residual image, with a network we call Error Transition Network (ETNet). The proposed model improves over the state-of-the-art methods with better semantic structures and more adaptive style pattern details. Various qualitative and quantitative experiments show that the key concept of both progressive strategy and error-correction leads to better results. Code and models are available at https://github.com/zhijieW94/ETNet.
Open AccessETNet: Error Transition Network for Arbitrary Style Transfer
Numerous valuable efforts have been devoted to achieving arbitrary style transfer since the seminal work of Gatys et al. However, existing state-of-the-art approaches often generate insufficiently stylized results under challenging cases. We believe a fundamental reason is that these approaches try to generate the stylized result in a single shot and hence fail to fully satisfy the constraints on semantic structures in the content images and style patterns in the style images. Inspired by the works on error-correction, instead, we propose a self-correcting model to predict what is wrong with the current stylization and refine it accordingly in an iterative manner. For each refinement, we transit the error features across both the spatial and scale domain and invert the processed features into a residual image, with a network we call Error Transition Network (ETNet). The proposed model improves over the state-of-the-art methods with better semantic structures and more adaptive style pattern details. Various qualitative and quantitative experiments show that the key concept of both progressive strategy and error-correction leads to better results. Code and models are available at https://github.com/zhijieW94/ETNet.
- Open Access
- 30 July 2018
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 37 (4) , 1-13
Non-stationary texture synthesis by adversarial expansion
The real world exhibits an abundance of non-stationary textures. Examples include textures with large scale structures, as well as spatially variant and inhomogeneous textures. While existing example-based texture synthesis methods can cope well with stationary textures, non-stationary textures still pose a considerable challenge, which remains unresolved. In this paper, we propose a new approach for example-based non-stationary texture synthesis. Our approach uses a generative adversarial network (GAN), trained to double the spatial extent of texture blocks extracted from a specific texture exemplar. Once trained, the fully convolutional generator is able to expand the size of the entire exemplar, as well as of any of its sub-blocks. We demonstrate that this conceptually simple approach is highly effective for capturing large scale structures, as well as other non-stationary attributes of the input exemplar. As a result, it can cope with challenging textures, which, to our knowledge, no other existing method can handle.
- 30 July 2018
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 37 (4) , 1-13
Open AccessNon-stationary texture synthesis by adversarial expansion
The real world exhibits an abundance of non-stationary textures. Examples include textures with large scale structures, as well as spatially variant and inhomogeneous textures. While existing example-based texture synthesis methods can cope well with stationary textures, non-stationary textures still pose a considerable challenge, which remains unresolved. In this paper, we propose a new approach for example-based non-stationary texture synthesis. Our approach uses a generative adversarial network (GAN), trained to double the spatial extent of texture blocks extracted from a specific texture exemplar. Once trained, the fully convolutional generator is able to expand the size of the entire exemplar, as well as of any of its sub-blocks. We demonstrate that this conceptually simple approach is highly effective for capturing large scale structures, as well as other non-stationary attributes of the input exemplar. As a result, it can cope with challenging textures, which, to our knowledge, no other existing method can handle.
- Open Access
- 30 July 2018
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 37 (4) , 1-11
Full 3D reconstruction of transparent objects
Numerous techniques have been proposed for reconstructing 3D models for opaque objects in past decades. However, none of them can be directly applied to transparent objects. This paper presents a fully automatic approach for reconstructing complete 3D shapes of transparent objects. Through positioning an object on a turntable, its silhouettes and light refraction paths under different viewing directions are captured. Then, starting from an initial rough model generated from space carving, our algorithm progressively optimizes the model under three constraints: surface and refraction normal consistency, surface projection and silhouette consistency, and surface smoothness. Experimental results on both synthetic and real objects demonstrate that our method can successfully recover the complex shapes of transparent objects and faithfully reproduce their light refraction properties.
- 30 July 2018
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 37 (4) , 1-11
Open AccessFull 3D reconstruction of transparent objects
Numerous techniques have been proposed for reconstructing 3D models for opaque objects in past decades. However, none of them can be directly applied to transparent objects. This paper presents a fully automatic approach for reconstructing complete 3D shapes of transparent objects. Through positioning an object on a turntable, its silhouettes and light refraction paths under different viewing directions are captured. Then, starting from an initial rough model generated from space carving, our algorithm progressively optimizes the model under three constraints: surface and refraction normal consistency, surface projection and silhouette consistency, and surface smoothness. Experimental results on both synthetic and real objects demonstrate that our method can successfully recover the complex shapes of transparent objects and faithfully reproduce their light refraction properties.