Shengyuan Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Shengyuan Zhang has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Zejian Li
Zhejiang University, Ningbo, China
6 shared publications - Lefan Hou
College of Computer Science and Technology, Zhejiang University, Hangzhou, China
3 shared publications Lingyun Sun
Zhejiang University
3 shared publications- Lingyun Sun
Zhejiang University, Hangzhou, China
3 shared publications Changyuan Yang
Alibaba Group
2 shared publications- Guang Yang
Alibaba Group
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) , 5088-5097
From Sketch to Reality: Enabling High-Quality, Cross-Category 3D Model Generation From Free-Hand Sketches With Minimal Data
This paper presents a novel approach for generating high-quality, cross-category 3D models from free-hand sketches with limited training data. We propose the first semi-supervised learning method to our knowledge for sketch-to-3D model conversion. Innovatively, we design a coarse-to-fine pipeline to perform the semi-supervised learning in the coarse stage and train a diffusion-based refiner to get a high-resolution 3D model. We designed a sketch-augmentation method for semi-supervised learning and integrated priors such as CLIP loss, shape prototypes, and adversarial loss to help generate high-quality results even with abstract and imprecise sketches. We also introduce an innovative procedural 3D generation method based on CAD code, which helps pre-train part of the network before fine-tuning with limited real data. Our approach, coupled with a specifically designed curriculum learning, allows us to generate high-quality 3D models across multiple categories with as few as 300 sketch-3D model pairs, marking a significant advancement over previous single-category approaches. In addition, we introduce the KO2D dataset, the largest collection of hand-drawn sketch-3D pairs to support further research in this area. As sketches are a far more intuitive and detailed way for users to express their unique ideas, we believe that this paper can move us closer to democratizing 3D content creation, enabling anyone to transform their ideas into 3D models effortlessly.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (7) , 5088-5097
From Sketch to Reality: Enabling High-Quality, Cross-Category 3D Model Generation From Free-Hand Sketches With Minimal Data
This paper presents a novel approach for generating high-quality, cross-category 3D models from free-hand sketches with limited training data. We propose the first semi-supervised learning method to our knowledge for sketch-to-3D model conversion. Innovatively, we design a coarse-to-fine pipeline to perform the semi-supervised learning in the coarse stage and train a diffusion-based refiner to get a high-resolution 3D model. We designed a sketch-augmentation method for semi-supervised learning and integrated priors such as CLIP loss, shape prototypes, and adversarial loss to help generate high-quality results even with abstract and imprecise sketches. We also introduce an innovative procedural 3D generation method based on CAD code, which helps pre-train part of the network before fine-tuning with limited real data. Our approach, coupled with a specifically designed curriculum learning, allows us to generate high-quality 3D models across multiple categories with as few as 300 sketch-3D model pairs, marking a significant advancement over previous single-category approaches. In addition, we introduce the KO2D dataset, the largest collection of hand-drawn sketch-3D pairs to support further research in this area. As sketches are a far more intuitive and detailed way for users to express their unique ideas, we believe that this paper can move us closer to democratizing 3D content creation, enabling anyone to transform their ideas into 3D models effortlessly.
- 17 April 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (5) , 234
SCoRE: Standardized Human Evaluation Provides a Reliable Measure for Semantic Consistency of Text-to-Image Generation
- 17 April 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (5) , 234
SCoRE: Standardized Human Evaluation Provides a Reliable Measure for Semantic Consistency of Text-to-Image Generation
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 9901-9910
Inversion-DPO: Precise and Efficient Post-Training for Diffusion Models
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 9901-9910
Open AccessInversion-DPO: Precise and Efficient Post-Training for Diffusion Models
- Open Access
Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completion
The application of diffusion models in 3D LiDAR scene completion is limited due to diffusion's slow sampling speed. Score distillation accelerates diffusion sampling but with performance degradation, while post-training with direct policy optimization (DPO) boosts performance using preference data. This paper proposes Distillation-DPO, a novel diffusion distillation framework for LiDAR scene completion with preference aligment. First, the student model generates paired completion scenes with different initial noises. Second, using LiDAR scene evaluation metrics as preference, we construct winning and losing sample pairs. Such construction is reasonable, since most LiDAR scene metrics are informative but non-differentiable to be optimized directly. Third, Distillation-DPO optimizes the student model by exploiting the difference in score functions between the teacher and student models on the paired completion scenes. Such procedure is repeated until convergence. Extensive experiments demonstrate that, compared to state-of-the-art LiDAR scene completion diffusion models, Distillation-DPO achieves higher-quality scene completion while accelerating the completion speed by more than 5-fold. Our method is the first to explore adopting preference learning in distillation to the best of our knowledge and provide insights into preference-aligned distillation. Our code is public available on https://github.com/happyw1nd/DistillationDPO.
Open AccessDiffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completion
The application of diffusion models in 3D LiDAR scene completion is limited due to diffusion's slow sampling speed. Score distillation accelerates diffusion sampling but with performance degradation, while post-training with direct policy optimization (DPO) boosts performance using preference data. This paper proposes Distillation-DPO, a novel diffusion distillation framework for LiDAR scene completion with preference aligment. First, the student model generates paired completion scenes with different initial noises. Second, using LiDAR scene evaluation metrics as preference, we construct winning and losing sample pairs. Such construction is reasonable, since most LiDAR scene metrics are informative but non-differentiable to be optimized directly. Third, Distillation-DPO optimizes the student model by exploiting the difference in score functions between the teacher and student models on the paired completion scenes. Such procedure is repeated until convergence. Extensive experiments demonstrate that, compared to state-of-the-art LiDAR scene completion diffusion models, Distillation-DPO achieves higher-quality scene completion while accelerating the completion speed by more than 5-fold. Our method is the first to explore adopting preference learning in distillation to the best of our knowledge and provide insights into preference-aligned distillation. Our code is public available on https://github.com/happyw1nd/DistillationDPO.
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (7) , 7686-7694
Reducing Spatial Fitting Error in Distillation of Denoising Diffusion Models
Denoising Diffusion models have exhibited remarkable capabilities in image generation. However, generating high-quality samples requires a large number of iterations. Knowledge distillation for diffusion models is an effective method to address this limitation with a shortened sampling process but causes degraded generative quality. Based on our analysis with bias-variance decomposition and experimental observations, we attribute the degradation to the spatial fitting error occurring in the training of both the teacher and student model in the distillation. Accordingly, we propose Spatial Fitting-Error Reduction Distillation model (SFERD). SFERD utilizes attention guidance from the teacher model and a designed semantic gradient predictor to reduce the student's fitting error. Empirically, our proposed model facilitates high-quality sample generation in a few function evaluations. We achieve an FID of 5.31 on CIFAR-10 and 9.39 on ImageNet 64x64 with only one step, outperforming existing diffusion methods. Our study provides a new perspective on diffusion distillation by highlighting the intrinsic denoising ability of models.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (7) , 7686-7694
Open AccessReducing Spatial Fitting Error in Distillation of Denoising Diffusion Models
Denoising Diffusion models have exhibited remarkable capabilities in image generation. However, generating high-quality samples requires a large number of iterations. Knowledge distillation for diffusion models is an effective method to address this limitation with a shortened sampling process but causes degraded generative quality. Based on our analysis with bias-variance decomposition and experimental observations, we attribute the degradation to the spatial fitting error occurring in the training of both the teacher and student model in the distillation. Accordingly, we propose Spatial Fitting-Error Reduction Distillation model (SFERD). SFERD utilizes attention guidance from the teacher model and a designed semantic gradient predictor to reduce the student's fitting error. Empirically, our proposed model facilitates high-quality sample generation in a few function evaluations. We achieve an FID of 5.31 on CIFAR-10 and 9.39 on ImageNet 64x64 with only one step, outperforming existing diffusion methods. Our study provides a new perspective on diffusion distillation by highlighting the intrinsic denoising ability of models.
- Open Access
Reducing Spatial Fitting Error in Distillation of Denoising Diffusion Models
Denoising Diffusion models have exhibited remarkable capabilities in image generation. However, generating high-quality samples requires a large number of iterations. Knowledge distillation for diffusion models is an effective method to address this limitation with a shortened sampling process but causes degraded generative quality. Based on our analysis with bias-variance decomposition and experimental observations, we attribute the degradation to the spatial fitting error occurring in the training of both the teacher and student model. Accordingly, we propose $\textbf{S}$patial $\textbf{F}$itting-$\textbf{E}$rror $\textbf{R}$eduction $\textbf{D}$istillation model ($\textbf{SFERD}$). SFERD utilizes attention guidance from the teacher model and a designed semantic gradient predictor to reduce the student's fitting error. Empirically, our proposed model facilitates high-quality sample generation in a few function evaluations. We achieve an FID of 5.31 on CIFAR-10 and 9.39 on ImageNet 64$\times$64 with only one step, outperforming existing diffusion methods. Our study provides a new perspective on diffusion distillation by highlighting the intrinsic denoising ability of models. Project link: \url{https://github.com/Sainzerjj/SFERD}.
Open AccessReducing Spatial Fitting Error in Distillation of Denoising Diffusion Models
Denoising Diffusion models have exhibited remarkable capabilities in image generation. However, generating high-quality samples requires a large number of iterations. Knowledge distillation for diffusion models is an effective method to address this limitation with a shortened sampling process but causes degraded generative quality. Based on our analysis with bias-variance decomposition and experimental observations, we attribute the degradation to the spatial fitting error occurring in the training of both the teacher and student model. Accordingly, we propose $\textbf{S}$patial $\textbf{F}$itting-$\textbf{E}$rror $\textbf{R}$eduction $\textbf{D}$istillation model ($\textbf{SFERD}$). SFERD utilizes attention guidance from the teacher model and a designed semantic gradient predictor to reduce the student's fitting error. Empirically, our proposed model facilitates high-quality sample generation in a few function evaluations. We achieve an FID of 5.31 on CIFAR-10 and 9.39 on ImageNet 64$\times$64 with only one step, outperforming existing diffusion methods. Our study provides a new perspective on diffusion distillation by highlighting the intrinsic denoising ability of models. Project link: \url{https://github.com/Sainzerjj/SFERD}.
- 17 December 2022
- Published by Springer Nature
- p. 30-41
Amodal Layout Completion in Complex Outdoor Scenes
- 17 December 2022
- Published by Springer Nature
- p. 30-41
Amodal Layout Completion in Complex Outdoor Scenes
- 1 January 2022
- Published by Springer Nature
- p. 520-531
FIGCI: Flow-Based Information-Geometric Causal Inference
- 1 January 2022
- Published by Springer Nature
- p. 520-531
FIGCI: Flow-Based Information-Geometric Causal Inference