Tian-Xing Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Tian-Xing Xu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Song-Hai Zhang
Tsinghua University, Beijing, China
2 shared publications - Bang Zhang
Alibaba, Hangzhou, China
1 shared publication - Fang-Lue Zhang
School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand
1 shared publication - Guan Luo
Tsinghua University, Beijing, China
1 shared publication - Guangyuan Wang
Tongyi Lab, Alibaba, Hangzhou, China
1 shared publication - Li Hu
Tongyi Lab, Alibaba, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessUCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 6627-6636
3D Gaussian Editing with A Single Image
The modeling and manipulation of 3D scenes captured from the real world are pivotal in various applications, attracting growing research interest. While previous works on editing have achieved interesting results through manipulating 3D meshes, they often require accurately reconstructed meshes to perform editing, which limits their application in 3D content generation. To address this gap, we introduce a novel single-image-driven 3D scene editing approach based on 3D Gaussian Splatting, enabling intuitive manipulation via directly editing the content on a 2D image plane. Our method learns to optimize the 3D Gaussians to align with an edited version of the image rendered from a user-specified viewpoint of the original scene. To capture long-range object deformation, we introduce positional loss into the optimization process of 3D Gaussian Splatting and enable gradient propagation through reparameterization. To handle occluded 3D Gaussians when rendering from the specified viewpoint, we build an anchor-based structure and employ a coarse-to-fine optimization strategy capable of handling long-range deformation while maintaining structural stability. Furthermore, we design a novel masking strategy to adaptively identify non-rigid deformation regions for fine-scale modeling. Extensive experiments show the effectiveness of our method in handling geometric details, long-range, and non-rigid deformation, demonstrating superior editing flexibility and quality compared to previous approaches.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 6627-6636
Open Access3D Gaussian Editing with A Single Image
The modeling and manipulation of 3D scenes captured from the real world are pivotal in various applications, attracting growing research interest. While previous works on editing have achieved interesting results through manipulating 3D meshes, they often require accurately reconstructed meshes to perform editing, which limits their application in 3D content generation. To address this gap, we introduce a novel single-image-driven 3D scene editing approach based on 3D Gaussian Splatting, enabling intuitive manipulation via directly editing the content on a 2D image plane. Our method learns to optimize the 3D Gaussians to align with an edited version of the image rendered from a user-specified viewpoint of the original scene. To capture long-range object deformation, we introduce positional loss into the optimization process of 3D Gaussian Splatting and enable gradient propagation through reparameterization. To handle occluded 3D Gaussians when rendering from the specified viewpoint, we build an anchor-based structure and employ a coarse-to-fine optimization strategy capable of handling long-range deformation while maintaining structural stability. Furthermore, we design a novel masking strategy to adaptively identify non-rigid deformation regions for fine-scale modeling. Extensive experiments show the effectiveness of our method in handling geometric details, long-range, and non-rigid deformation, demonstrating superior editing flexibility and quality compared to previous approaches.