Yu-Wei Zhang
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
Yu-Wei Zhang has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Caiming Zhang
School of Software, Shandong University, Jinan, People’s Republic of China
7 shared publications - Yanzhao Chen
School of Mechanical and Automotive Engineering Qilu University of Technology (Shandong Academy of Sciences) Jinan China
7 shared publications - Hui Liu
College of Computer and Information Engineering Nanjing Tech University 211800 Nanjing China
6 shared publications - Zhongping Ji
Hangzhou Dianzi University
5 shared publications - Wenping Wang
Texas A&M University, College Station, USA
3 shared publications Caiming Zhang
Shandong Univ, Software Coll, Jinan, Shandong, Peoples R China
2 shared publications
Latest Publications
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (7) , 5761-5772
MonoRelief V2: Leveraging Real Data for High-Fidelity Monocular Relief Recovery
This paper presents MonoRelief V2, an end-to-end model designed for directly recovering 2.5D reliefs from single images under complex material and illumination variations. In contrast to its predecessor, MonoRelief V1 (Gao et al. 2025), which was solely trained on synthetic data, MonoRelief V2 incorporates real data to achieve improved robustness, accuracy and efficiency. To overcome the challenge of acquiring large-scale real-world dataset, we generate approximately 15,000 pseudo-real images using a text-to-image generative model, and derive corresponding depth pseudo-labels through fusion of depth and normal predictions. Furthermore, we construct a small-scale real-world dataset (800 samples) via multi-view reconstruction and detail refinement. MonoRelief V2 is then progressively trained on the pseudo-real and real-world datasets. Comprehensive experiments demonstrate its state-of-the-art performance both in depth and normal predictions, highlighting its strong potential for a range of downstream applications.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (7) , 5761-5772
MonoRelief V2: Leveraging Real Data for High-Fidelity Monocular Relief Recovery
This paper presents MonoRelief V2, an end-to-end model designed for directly recovering 2.5D reliefs from single images under complex material and illumination variations. In contrast to its predecessor, MonoRelief V1 (Gao et al. 2025), which was solely trained on synthetic data, MonoRelief V2 incorporates real data to achieve improved robustness, accuracy and efficiency. To overcome the challenge of acquiring large-scale real-world dataset, we generate approximately 15,000 pseudo-real images using a text-to-image generative model, and derive corresponding depth pseudo-labels through fusion of depth and normal predictions. Furthermore, we construct a small-scale real-world dataset (800 samples) via multi-view reconstruction and detail refinement. MonoRelief V2 is then progressively trained on the pseudo-real and real-world datasets. Comprehensive experiments demonstrate its state-of-the-art performance both in depth and normal predictions, highlighting its strong potential for a range of downstream applications.
- 16 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (10) , 7986-7997
MonoRelief: Recovering 2.5D Relief From a Single Image
In this article, we introduce MonoRelief, a novel method that combines the strengths of a depth map and a normal map to achieve high-quality relief recovery from a single image. By constructing a large-scale relief dataset that encompasses a diverse range of relief shapes, materials, and lighting conditions, we enable the training of a robust normal estimation network capable of handling various types of relief images. Furthermore, we leverage the state-of-the-art method, DepthAnything v2 (Yang et al. 2024), to generate depth maps from the input images. By integrating the strengths of both maps, MonoRelief recovers 2.5D reliefs with reasonable depth structures and intricate geometrical details. We validate the effectiveness and robustness of MonoRelief through comprehensive experiments, and showcase its potential in a variety of downstream applications, including Image-to-Relief, Text-to-Relief, Lines-to-Relief and relief reproduction.
- 16 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (10) , 7986-7997
MonoRelief: Recovering 2.5D Relief From a Single Image
In this article, we introduce MonoRelief, a novel method that combines the strengths of a depth map and a normal map to achieve high-quality relief recovery from a single image. By constructing a large-scale relief dataset that encompasses a diverse range of relief shapes, materials, and lighting conditions, we enable the training of a robust normal estimation network capable of handling various types of relief images. Furthermore, we leverage the state-of-the-art method, DepthAnything v2 (Yang et al. 2024), to generate depth maps from the input images. By integrating the strengths of both maps, MonoRelief recovers 2.5D reliefs with reasonable depth structures and intricate geometrical details. We validate the effectiveness and robustness of MonoRelief through comprehensive experiments, and showcase its potential in a variety of downstream applications, including Image-to-Relief, Text-to-Relief, Lines-to-Relief and relief reproduction.
- 31 December 2023
- Published by Social Innovation Corporation Institute (SICI) in Innovation Enterprise Research
- Vol. 8 (4) , 265-284
A Comparative Study on Preference for Chinese Consumer Delivery App Selectiong Factors Using AHP: Focusing on Meituan and Ele.me
본 연구는 중국 배달 애플리케이션을 이용한 소비자의 배달앱 선택요인 우선순위 및 메이퇀·어러머의 선호도를 파악하기 위해 선행연구를 바탕으로 배달앱 선택요인을 설정하고, 중국 메이퇀과 어러머에서 일하는 배달업 종업원을 대상으로 설문조사를 실시하여 AHP 분석으로 결과를 얻었다.첫째, 배달앱 선택요인의 상위요인에 있어서 서비스를 가장 중요시하는 것으로 나타났으며, 다음에 경제성, 정보품질, 시스템품질 등 순으로 나타났다. 둘째, 배달앱 선택요인의 하위요인에 있어서 애프터서비스를 가장 중요시하고, 가격, 배달요금이 높은 중요도를 차지하고 있다. 그리고 할인 혜택, 정확성, 배달 속도 등도 상대적으로 높은 중요도를 차지하고 있다. 반면 서비스 태도, 신뢰성, 안전성 등은 상대적으로 낮은 중요도를 차지하였다. 다양성, 편리성, 디자인 등도 더 낮은 중요도를 차지하였다. 셋째, 평가 대안의 종합결과를 살펴보면 메이퇀은 어러머보다 중요도가 더 높게 나타났다. 메이퇀은 가격, 배달요금, 편리성, 다양성, 정확성, 배달 속도, 서비스 태도, 애프터서비스 등 측면에서 1위를 차지하였으며, 어러머는 할인 혜택, 안전성, 디자인 등 측면에서 1위를 차지하였다.연구결과를 통해 중국 배달앱 이용하는 소비자들의 배달앱 선택요인 및 선호도에 대한 근본적인 이해를 얻고, 우선순위의 제시를 통하여 배달앱 제공업체의 경쟁력 향상을 위한 실무적 전략방안을 제시하고자 한다.
- 31 December 2023
- Published by Social Innovation Corporation Institute (SICI) in Innovation Enterprise Research
- Vol. 8 (4) , 265-284
A Comparative Study on Preference for Chinese Consumer Delivery App Selectiong Factors Using AHP: Focusing on Meituan and Ele.me
본 연구는 중국 배달 애플리케이션을 이용한 소비자의 배달앱 선택요인 우선순위 및 메이퇀·어러머의 선호도를 파악하기 위해 선행연구를 바탕으로 배달앱 선택요인을 설정하고, 중국 메이퇀과 어러머에서 일하는 배달업 종업원을 대상으로 설문조사를 실시하여 AHP 분석으로 결과를 얻었다.첫째, 배달앱 선택요인의 상위요인에 있어서 서비스를 가장 중요시하는 것으로 나타났으며, 다음에 경제성, 정보품질, 시스템품질 등 순으로 나타났다. 둘째, 배달앱 선택요인의 하위요인에 있어서 애프터서비스를 가장 중요시하고, 가격, 배달요금이 높은 중요도를 차지하고 있다. 그리고 할인 혜택, 정확성, 배달 속도 등도 상대적으로 높은 중요도를 차지하고 있다. 반면 서비스 태도, 신뢰성, 안전성 등은 상대적으로 낮은 중요도를 차지하였다. 다양성, 편리성, 디자인 등도 더 낮은 중요도를 차지하였다. 셋째, 평가 대안의 종합결과를 살펴보면 메이퇀은 어러머보다 중요도가 더 높게 나타났다. 메이퇀은 가격, 배달요금, 편리성, 다양성, 정확성, 배달 속도, 서비스 태도, 애프터서비스 등 측면에서 1위를 차지하였으며, 어러머는 할인 혜택, 안전성, 디자인 등 측면에서 1위를 차지하였다.연구결과를 통해 중국 배달앱 이용하는 소비자들의 배달앱 선택요인 및 선호도에 대한 근본적인 이해를 얻고, 우선순위의 제시를 통하여 배달앱 제공업체의 경쟁력 향상을 위한 실무적 전략방안을 제시하고자 한다.
- 22 September 2023
- Published by U-turn Press LLC in Computer-Aided Design and Applications
A Review of Human Pose Estimation Methods in Markerless Motion Capture
Computer-Aided Design and Applications is an international journal on the applications of CAD and CAM. It publishes papers in the general domain of CAD plus in emerging fields like bio-CAD, nano-CAD, soft-CAD, garment-CAD, PLM, PDM, CAD data mining, CAD and the internet, CAD education, genetic algorithms and CAD engines. The journal is aimed at all developers and users of CAD technology to ptovide CAD solutions for various stages of design and manufacturing. The journal publishes all about Computer-Aided Design and Computer-Aided technologies.
- 22 September 2023
- Published by U-turn Press LLC in Computer-Aided Design and Applications
A Review of Human Pose Estimation Methods in Markerless Motion Capture
Computer-Aided Design and Applications is an international journal on the applications of CAD and CAM. It publishes papers in the general domain of CAD plus in emerging fields like bio-CAD, nano-CAD, soft-CAD, garment-CAD, PLM, PDM, CAD data mining, CAD and the internet, CAD education, genetic algorithms and CAD engines. The journal is aimed at all developers and users of CAD technology to ptovide CAD solutions for various stages of design and manufacturing. The journal publishes all about Computer-Aided Design and Computer-Aided technologies.
- 8 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 29 (12) , 5008-5019
Neural Modeling of Portrait Bas-Relief From a Single Photograph
In this paper, we present an end-to-end neural solution to model portrait bas-relief from a single photograph, which is cast as a problem of image-to-depth translation. The main challenge is the lack of bas-relief data for network training. To solve this problem, we propose a semi-automatic pipeline to synthesize bas-relief samples. The main idea is to first construct normal maps from photos, and then generate bas-relief samples by reconstructing pixel-wise depths. In total, our synthetic dataset contains 23 k pixel-wise photo/bas-relief pairs. Since the process of bas-relief synthesis requires a certain amount of user interactions, we propose end-to-end solutions with various network architectures, and train them on the synthetic data. We select the one that gave the best results through qualitative and quantitative comparisons. Experiments on numerous portrait photos, comparisons with state-of-the-art methods and evaluations by artists have proven the effectiveness and efficiency of the selected network.
- 8 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 29 (12) , 5008-5019
Neural Modeling of Portrait Bas-Relief From a Single Photograph
In this paper, we present an end-to-end neural solution to model portrait bas-relief from a single photograph, which is cast as a problem of image-to-depth translation. The main challenge is the lack of bas-relief data for network training. To solve this problem, we propose a semi-automatic pipeline to synthesize bas-relief samples. The main idea is to first construct normal maps from photos, and then generate bas-relief samples by reconstructing pixel-wise depths. In total, our synthetic dataset contains 23 k pixel-wise photo/bas-relief pairs. Since the process of bas-relief synthesis requires a certain amount of user interactions, we propose end-to-end solutions with various network architectures, and train them on the synthetic data. We select the one that gave the best results through qualitative and quantitative comparisons. Experiments on numerous portrait photos, comparisons with state-of-the-art methods and evaluations by artists have proven the effectiveness and efficiency of the selected network.
- 28 July 2021
- Published by U-turn Press LLC in Computer-Aided Design and Applications
- Vol. 19 (2)
High Relief Modeling from 3D Object Through Laplacian-based Surface Deformation
- 28 July 2021
- Published by U-turn Press LLC in Computer-Aided Design and Applications
- Vol. 19 (2)
High Relief Modeling from 3D Object Through Laplacian-based Surface Deformation
- 24 May 2021
- Published by Wiley in Computer Graphics Forum
- Vol. 40 (6) , 288-303
Neural Modelling of Flower Bas‐relief from 2D Line Drawing
- 24 May 2021
- Published by Wiley in Computer Graphics Forum
- Vol. 40 (6) , 288-303
Neural Modelling of Flower Bas‐relief from 2D Line Drawing
- 18 July 2020
- Published by Springer Nature in The Visual Computer
- Vol. 36 (10-12) , 2241-2250
A fast solution for Chinese calligraphy relief modeling from 2D handwriting image
- 18 July 2020
- Published by Springer Nature in The Visual Computer
- Vol. 36 (10-12) , 2241-2250
A fast solution for Chinese calligraphy relief modeling from 2D handwriting image
- 1 June 2020
- Published by Elsevier in Computer Aided Geometric Design
- Vol. 80
Example-driven modeling of portrait bas-relief
- 1 June 2020
- Published by Elsevier in Computer Aided Geometric Design
- Vol. 80
Example-driven modeling of portrait bas-relief
- 10 May 2020
- Published by Wiley in Computer Graphics Forum
- Vol. 39 (6) , 258-268
From 2.5D Bas‐relief to 3D Portrait Model
In contrast to 3D model that can be freely observed, p ortrait bas‐relief projects slightly from the background and is limited by fixed viewpoint. In this paper, we propose a novel method to reconstruct the underlying 3D shape from a single 2.5D bas‐relief, providing observers wider viewing perspectives. Our target is to make the reconstructed portrait has natural depth ordering and similar appearance to the input. To achieve this, we first use a 3D template face to fit the portrait. Then, we optimize the face shape by normal transfer and Poisson surface reconstruction. The hair and body regions are finally reconstructed and combined with the 3D face. From the resulting 3D shape, one can generate new reliefs with varying poses and thickness, freeing the input one from fixed view. A number of experimental results verify the effectiveness of our method.
- 10 May 2020
- Published by Wiley in Computer Graphics Forum
- Vol. 39 (6) , 258-268
From 2.5D Bas‐relief to 3D Portrait Model
In contrast to 3D model that can be freely observed, p ortrait bas‐relief projects slightly from the background and is limited by fixed viewpoint. In this paper, we propose a novel method to reconstruct the underlying 3D shape from a single 2.5D bas‐relief, providing observers wider viewing perspectives. Our target is to make the reconstructed portrait has natural depth ordering and similar appearance to the input. To achieve this, we first use a 3D template face to fit the portrait. Then, we optimize the face shape by normal transfer and Poisson surface reconstruction. The hair and body regions are finally reconstructed and combined with the 3D face. From the resulting 3D shape, one can generate new reliefs with varying poses and thickness, freeing the input one from fixed view. A number of experimental results verify the effectiveness of our method.