Jieqing Feng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jieqing Feng has a total of 122 co-authors. Here are the top co-authors by number of shared publications:
Yuhong Zhao
10 shared publications- Xiaogang Jin
Zhejiang University
7 shared publications Xiaoxia Lin
7 shared publicationsZengqiang Liu
5 shared publicationsLei Wang
State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China
4 shared publicationsWenjun Huang
4 shared publications
Latest Publications
- Open Access
- 29 September 2026
- Published by Springer Nature in Visual Computing for Industry, Biomedicine, and Art
- Vol. 9 (1) , 22
IP-ConTex: detail-consistent texture generation with image prompt
Textures are critical for enhancing the visual fidelity and diversity of three-dimensional (3D) models. Recently, generative models have significantly advanced texture generation. However, fine-grained control of the generation process remains challenging. Hence, we propose IP-ConTex, which is a novel image-guided texture-generation method that introduces appearance control into the diffusion process to ensure detail-consistent results. First, synchronized multiview diffusion is employed to maintain structural and layout consistency across multiple views. Subsequently, a new appearance-control module is designed for the pretrained diffusion model. By leveraging cross-attention control, self-attention control, diffusion feature synchronization, and color adjustment, appearance information from the reference image is effectively extracted and injected into the texture-generation process. Experimental results demonstrate that IP-ConTex successfully transfers appearance details to 3D geometries without fine-tuning or optimization, thus achieving high-quality and detail-consistent texture generation.
- 29 September 2026
- Published by Springer Nature in Visual Computing for Industry, Biomedicine, and Art
- Vol. 9 (1) , 22
Open AccessIP-ConTex: detail-consistent texture generation with image prompt
Textures are critical for enhancing the visual fidelity and diversity of three-dimensional (3D) models. Recently, generative models have significantly advanced texture generation. However, fine-grained control of the generation process remains challenging. Hence, we propose IP-ConTex, which is a novel image-guided texture-generation method that introduces appearance control into the diffusion process to ensure detail-consistent results. First, synchronized multiview diffusion is employed to maintain structural and layout consistency across multiple views. Subsequently, a new appearance-control module is designed for the pretrained diffusion model. By leveraging cross-attention control, self-attention control, diffusion feature synchronization, and color adjustment, appearance information from the reference image is effectively extracted and injected into the texture-generation process. Experimental results demonstrate that IP-ConTex successfully transfers appearance details to 3D geometries without fine-tuning or optimization, thus achieving high-quality and detail-consistent texture generation.
- 15 September 2026
- Published by Elsevier in Computer-Aided Design
- Vol. 202
Efficient and accurate Bernstein polynomial composition via monomial-basis transformation
- 15 September 2026
- Published by Elsevier in Computer-Aided Design
- Vol. 202
Efficient and accurate Bernstein polynomial composition via monomial-basis transformation
- Open Access
- 20 July 2026
- Published by Elsevier in Visual Informatics
ARCAim: Hardware-accelerated differentiable ray tracing for adaptive heliostat aiming
- 20 July 2026
- Published by Elsevier in Visual Informatics
Open AccessARCAim: Hardware-accelerated differentiable ray tracing for adaptive heliostat aiming
- Open Access
- 31 May 2026
- Published by Elsevier in SSRN Electronic Journal
Efficient and Accurate Bernstein Polynomial Composition via Monomial-Basis Transformation
Bernstein polynomial composition refers to composing two Bernstein polynomial functions into a new Bernstein polynomial function, and computing the coefficients of the resulting polynomial function based on the coefficients of the input functions. As a fundamental operation in computer-aided geometric design (CAGD), Bernstein polynomial composition is widely used for modeling and processing of parametric curves, surfaces, and parametric volumes. Achieving both high efficiency and numerical stability in Bernstein polynomial composition remains a challenging problem in CAGD. In this paper, a new composition method is proposed. The method is based on basis transformation and polynomial composition in the monomial basis, and it applies to both Bézier simplexes and tensor-product Bézier functions of arbitrary degree and dimension. Through basis transformation, the proposed method converts the composition problem from the Bernstein basis, which is more suitable for geometric representation, to the monomial basis, which is more suitable for algebraic computation, thereby ensuring computational efficiency and reducing implementation complexity. By leveraging the mathematical property that input degrees are low and output degrees are high in composition operations, the method confines the numerically unstable Bernstein-to-Monomial basis transformation to low-degree inputs, avoiding the numerical risks of high-degree basis transformations. By generalizing the nested structure of Horner's method to the composition of polynomial coefficients, the method achieves further improvements in both efficiency and numerical stability. Additionally, all three basis transformation matrices involved can be pre-computed and stored. Theoretical analysis and experimental results demonstrate that the proposed method significantly improves computational efficiency and reduces implementation complexity, while maintaining high numerical accuracy.
- 31 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessEfficient and Accurate Bernstein Polynomial Composition via Monomial-Basis Transformation
Bernstein polynomial composition refers to composing two Bernstein polynomial functions into a new Bernstein polynomial function, and computing the coefficients of the resulting polynomial function based on the coefficients of the input functions. As a fundamental operation in computer-aided geometric design (CAGD), Bernstein polynomial composition is widely used for modeling and processing of parametric curves, surfaces, and parametric volumes. Achieving both high efficiency and numerical stability in Bernstein polynomial composition remains a challenging problem in CAGD. In this paper, a new composition method is proposed. The method is based on basis transformation and polynomial composition in the monomial basis, and it applies to both Bézier simplexes and tensor-product Bézier functions of arbitrary degree and dimension. Through basis transformation, the proposed method converts the composition problem from the Bernstein basis, which is more suitable for geometric representation, to the monomial basis, which is more suitable for algebraic computation, thereby ensuring computational efficiency and reducing implementation complexity. By leveraging the mathematical property that input degrees are low and output degrees are high in composition operations, the method confines the numerically unstable Bernstein-to-Monomial basis transformation to low-degree inputs, avoiding the numerical risks of high-degree basis transformations. By generalizing the nested structure of Horner's method to the composition of polynomial coefficients, the method achieves further improvements in both efficiency and numerical stability. Additionally, all three basis transformation matrices involved can be pre-computed and stored. Theoretical analysis and experimental results demonstrate that the proposed method significantly improves computational efficiency and reduces implementation complexity, while maintaining high numerical accuracy.
- 9 January 2026
- Published by Elsevier in Renewable Energy
- Vol. 261
Fast annual energy estimation for solar tower power systems based on heliostat grouping and solar position sampling
- 9 January 2026
- Published by Elsevier in Renewable Energy
- Vol. 261
Fast annual energy estimation for solar tower power systems based on heliostat grouping and solar position sampling
- 17 December 2025
- Published by Elsevier in Journal of Structural Biology
- Vol. 218 (1) , 108281
Adaptive Gaussian representation for differentiable cryo-electron tomography reconstruction
- 17 December 2025
- Published by Elsevier in Journal of Structural Biology
- Vol. 218 (1) , 108281
Adaptive Gaussian representation for differentiable cryo-electron tomography reconstruction
- 28 August 2025
- Published by Elsevier in Solar Energy
- Vol. 301
The optimization of heliostat paraboloid canting via differentiable ray tracing
- 28 August 2025
- Published by Elsevier in Solar Energy
- Vol. 301
The optimization of heliostat paraboloid canting via differentiable ray tracing
- 14 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (1) , 874-886
Boundary-Aware Consistent Normal Orientation for Point Clouds
Inferring a globally consistent normal orientation for point clouds remains challenging, especially for noisy and non-watertight point clouds. To improve accuracy and robustness in orientation inference, a Boundary-Aware Consistent Normal Orientation (BACNO) method is proposed. Its main idea is to transform the normal orientation problem into a boundary-aware narrow band grid partitioning problem. This processing process is as follows: First, an unsigned distance field for an input point cloud is computed, which is defined on a regular grid. The field is then trimmed as a boundary-aware narrow band grid around the point cloud. Next, the narrow band grid is segmented into two parts, with each part located on one side of the input point cloud. Finally, a coarse-to-fine normal orientation strategy is presented to achieve the globally consistent orientation. Extensive experimental results demonstrate that the proposed method outperforms state-of-the-art methods, particularly for noisy and non-watertight point clouds.
- 14 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (1) , 874-886
Boundary-Aware Consistent Normal Orientation for Point Clouds
Inferring a globally consistent normal orientation for point clouds remains challenging, especially for noisy and non-watertight point clouds. To improve accuracy and robustness in orientation inference, a Boundary-Aware Consistent Normal Orientation (BACNO) method is proposed. Its main idea is to transform the normal orientation problem into a boundary-aware narrow band grid partitioning problem. This processing process is as follows: First, an unsigned distance field for an input point cloud is computed, which is defined on a regular grid. The field is then trimmed as a boundary-aware narrow band grid around the point cloud. Next, the narrow band grid is segmented into two parts, with each part located on one side of the input point cloud. Finally, a coarse-to-fine normal orientation strategy is presented to achieve the globally consistent orientation. Extensive experimental results demonstrate that the proposed method outperforms state-of-the-art methods, particularly for noisy and non-watertight point clouds.
- 9 August 2025
- Published by Elsevier in Computers & Graphics
- Vol. 132
A parameterization method for B-spline curve interpolation via supervised regression
- 9 August 2025
- Published by Elsevier in Computers & Graphics
- Vol. 132
A parameterization method for B-spline curve interpolation via supervised regression
- Open Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Feature-Preserving Mesh Repair via Restricted Power Diagram
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessFeature-Preserving Mesh Repair via Restricted Power Diagram