publications

2026

1. SiggraphAsia

   

   Artic-O: End-to-End Articulated Object Reconstruction via Latent Geometry Learning

   Xuyang Wang, Zhenyu Li, Jian Ding, and 4 more authors

   Siggraph Asia, 2026

   End-to-end articulated object reconstruction from sparse multi-state images, leveraging latent geometry priors to recover complete 3D shape, movable parts, and articulation parameters, while reducing inference time from about 9 minutes to 0.32 seconds per object.

   arXiv Bib Code

   @article{wang2026artico,
     title = {{Artic-O}: End-to-End Articulated Object Reconstruction via Latent Geometry Learning},
     author = {Wang, Xuyang and Li, Zhenyu and Ding, Jian and Slim, Habib and Wonka, Peter and Li, Hongdong and Elhoseiny, Mohamed},
     journal = {Siggraph Asia},
     year = {2026},
     note = {End-to-end articulated object reconstruction from sparse multi-state images, leveraging latent geometry priors to recover complete 3D shape, movable parts, and articulation parameters, while reducing inference time from about 9 minutes to 0.32 seconds per object.
     },
     github = {https://wxyxixixi.github.io/Artic-O/}
   }

2025

1. arXiv

   

   DoubleDiffusion: Combining Heat Diffusion with Denoising Diffusion for Texture Generation on 3D Meshes

   Xuyang Wang, Ziang Cheng, Zhenyu Li, and 6 more authors

   arXiv, 2025

   Treating 3D meshes as known manifolds and leveraging heat diffusion kernels as intrinsic operators for generative modeling of texture signals directly on mesh surfaces.

   arXiv Bib Code

   @article{wang2025doublediffusion,
     title = {DoubleDiffusion: Combining Heat Diffusion with Denoising Diffusion for Texture Generation on 3D Meshes},
     author = {Wang, Xuyang and Cheng, Ziang and Li, Zhenyu and Yang, Jiayu and Ji, Haorui and Ji, Pan and Harandi, Mehrtash and Hartley, Richard and Li, Hongdong},
     year = {2025},
     publisher = {arXiv},
     journal = {arXiv},
     note = {Treating 3D meshes as known manifolds and leveraging heat diffusion kernels as intrinsic operators for generative modeling of texture signals directly on mesh surfaces.},
     github = {Wxyxixixi/DoubleDiffusion_3D_Mesh}
   }

2024

1. TIP

   

   Binsformer: Revisiting adaptive bins for monocular depth estimation

   Zhenyu Li, Xuyang Wang, Xianming Liu, and 1 more author

   IEEE Transactions on Image Processing, 2024

   arXiv Bib Code

   @article{li2024binsformer,
     title = {Binsformer: Revisiting adaptive bins for monocular depth estimation},
     author = {Li, Zhenyu and Wang, Xuyang and Liu, Xianming and Jiang, Junjun},
     journal = {IEEE Transactions on Image Processing},
     year = {2024},
     publisher = {IEEE},
     github = {zhyever/Monocular-Depth-Estimation-Toolbox}
   }