no code implementations • 15 Apr 2024 • Tianhan Xu, Takuya Ikeda, Koichi Nishiwaki
In this paper, we propose a method to segment and recover a static, clean background and multiple 360$^\circ$ objects from observations of scenes at different timestamps.
no code implementations • 1 Feb 2024 • Tianhan Xu, Zhe Hu, Ling Chen, Bin Li
In the next stage, we train the skill router using task-specific downstream data and use this router to integrate the acquired skills with LLMs during inference.
no code implementations • 25 Jul 2022 • Tianhan Xu, Tatsuya Harada
Recent advances in radiance fields enable photorealistic rendering of static or dynamic 3D scenes, but still do not support explicit deformation that is used for scene manipulation or animation.
no code implementations • CVPR 2022 • Tianhan Xu, Yasuhiro Fujita, Eiichi Matsumoto
Our method defines the neural scene representation on the mesh surface points and signed distances from the surface of a human body mesh.
1 code implementation • CVPR 2021 • Tianhan Xu, Wataru Takano
In this paper, we propose a novel graph convolutional network architecture, Graph Stacked Hourglass Networks, for 2D-to-3D human pose estimation tasks.
Ranked #53 on 3D Human Pose Estimation on MPI-INF-3DHP (AUC metric)