Qun-Ce Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qun-Ce Xu has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Tai-Jiang Mu
Tsinghua University
4 shared publications - Yong-Liang Yang
University of Bath
4 shared publications - Hao-Xiang Chen
Tsinghua University, Beijing, China
3 shared publications - Qi-Yuan Feng
CS Dept, Tsinghua University, BEIJING, China
2 shared publications Shi-Min Hu
Department of Computer Science and Technology, Tsinghua University, Beijing, China
2 shared publications- Shi-Min Hu
Tsinghua University
2 shared publications
Latest Publications
- 31 July 2026
- Published by Springer Nature in Science China Information Sciences
- Vol. 69 (8) , 182102
Motion-driven 4D scene generation
- 31 July 2026
- Published by Springer Nature in Science China Information Sciences
- Vol. 69 (8) , 182102
Motion-driven 4D scene generation
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (6) , 7524-7531
FlowSSC: Universal Generative Monocular Semantic Scene Completion via One-Step Latent Diffusion
Semantic Scene Completion (SSC) from monocular RGB images is a fundamental yet challenging task due to the inherent ambiguity of inferring occluded 3D geometry from a single view. While feed-forward methods have made progress, they often struggle to generate plausible details in occluded regions and preserve the fundamental spatial relationships of objects. Such accurate generative reasoning capability for the entire 3D space is critical in real-world applications. In this paper, we present FlowSSC, the first generative framework applied directly to monocular semantic scene completion. FlowSSC treats the SSC task as a conditional generation problem and can seamlessly integrate with existing feed-forward SSC methods to significantly boost their performance. To achieve real-time inference without compromising quality, we introduce Shortcut Flow-matching that operates in a compact triplane latent space. Unlike standard diffusion models that require hundreds of steps, our method utilizes a shortcut mechanism to achieve high-fidelity generation in a single step, enabling practical deployment in autonomous systems. Extensive experiments on SemanticKITTI demonstrate that FlowSSC achieves state-of-the-art performance, significantly outperforming existing baselines.
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (6) , 7524-7531
FlowSSC: Universal Generative Monocular Semantic Scene Completion via One-Step Latent Diffusion
Semantic Scene Completion (SSC) from monocular RGB images is a fundamental yet challenging task due to the inherent ambiguity of inferring occluded 3D geometry from a single view. While feed-forward methods have made progress, they often struggle to generate plausible details in occluded regions and preserve the fundamental spatial relationships of objects. Such accurate generative reasoning capability for the entire 3D space is critical in real-world applications. In this paper, we present FlowSSC, the first generative framework applied directly to monocular semantic scene completion. FlowSSC treats the SSC task as a conditional generation problem and can seamlessly integrate with existing feed-forward SSC methods to significantly boost their performance. To achieve real-time inference without compromising quality, we introduce Shortcut Flow-matching that operates in a compact triplane latent space. Unlike standard diffusion models that require hundreds of steps, our method utilizes a shortcut mechanism to achieve high-fidelity generation in a single step, enabling practical deployment in autonomous systems. Extensive experiments on SemanticKITTI demonstrate that FlowSSC achieves state-of-the-art performance, significantly outperforming existing baselines.
- 15 August 2025
- Published by Elsevier in Computers & Graphics
- Vol. 132
SDLKF: Signed Distance Linear Kernel Function for surface reconstruction
- 15 August 2025
- Published by Elsevier in Computers & Graphics
- Vol. 132
SDLKF: Signed Distance Linear Kernel Function for surface reconstruction
- 26 April 2025
- Published by Springer Nature
- p. 194-215
High-Accuracy Fractured Object Reassembly Under Arbitrary Poses
- 26 April 2025
- Published by Springer Nature
- p. 194-215
High-Accuracy Fractured Object Reassembly Under Arbitrary Poses
- Open Access
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
FragmentDiff: A Diffusion Model for Fractured Object Assembly
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessFragmentDiff: A Diffusion Model for Fractured Object Assembly
- Open Access
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
EVSplitting: An Efficient and Visually Consistent Splitting Algorithm for 3D Gaussian Splatting
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessEVSplitting: An Efficient and Visually Consistent Splitting Algorithm for 3D Gaussian Splatting
- Open Access
- 18 March 2024
- Published by Elsevier in Graphical Models
- Vol. 133
Point cloud denoising using a generalized error metric
- 18 March 2024
- Published by Elsevier in Graphical Models
- Vol. 133
Open AccessPoint cloud denoising using a generalized error metric
- Open Access
- 1 September 2023
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 9 (3) , 407-442
A survey of deep learning-based 3D shape generation
Deep learning has been successfully used for tasks in the 2D image domain. Research on 3D computer vision and deep geometry learning has also attracted attention. Considerable achievements have been made regarding feature extraction and discrimination of 3D shapes. Following recent advances in deep generative models such as generative adversarial networks, effective generation of 3D shapes has become an active research topic. Unlike 2D images with a regular grid structure, 3D shapes have various representations, such as voxels, point clouds, meshes, and implicit functions. For deep learning of 3D shapes, shape representation has to be taken into account as there is no unified representation that can cover all tasks well. Factors such as the representativeness of geometry and topology often largely affect the quality of the generated 3D shapes. In this survey, we comprehensively review works on deep-learning-based 3D shape generation by classifying and discussing them in terms of the underlying shape representation and the architecture of the shape generator. The advantages and disadvantages of each class are further analyzed. We also consider the 3D shape datasets commonly used for shape generation. Finally, we present several potential research directions that hopefully can inspire future works on this topic.
- 1 September 2023
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 9 (3) , 407-442
Open AccessA survey of deep learning-based 3D shape generation
Deep learning has been successfully used for tasks in the 2D image domain. Research on 3D computer vision and deep geometry learning has also attracted attention. Considerable achievements have been made regarding feature extraction and discrimination of 3D shapes. Following recent advances in deep generative models such as generative adversarial networks, effective generation of 3D shapes has become an active research topic. Unlike 2D images with a regular grid structure, 3D shapes have various representations, such as voxels, point clouds, meshes, and implicit functions. For deep learning of 3D shapes, shape representation has to be taken into account as there is no unified representation that can cover all tasks well. Factors such as the representativeness of geometry and topology often largely affect the quality of the generated 3D shapes. In this survey, we comprehensively review works on deep-learning-based 3D shape generation by classifying and discussing them in terms of the underlying shape representation and the architecture of the shape generator. The advantages and disadvantages of each class are further analyzed. We also consider the 3D shape datasets commonly used for shape generation. Finally, we present several potential research directions that hopefully can inspire future works on this topic.