|
Narrator: Towards Natural Control of Human-Scene Interaction Generation via Relationship Reasoning
Haibiao Xuan, Xiongzheng Li, Jinsong Zhang, Hongwen Zhang, Yebin Liu, and Kun Li
IEEE International Conference on Computer Vision (ICCV), Poster, 2023.
[Project]
[PDF]
[Code]
[BibTeX]
We propose a novel relationship reasoning-based generative approach, Narrator, for naturally controllable generation given a 3D scene and a textual description.
|
|
MH-HMR: Human Mesh Recovery from Monocular Images via Multi-Hypothesis Learning
Haibiao Xuan, Jinsong Zhang, Yu-Kun Lai, and Kun Li
CACAI 2022 (Oral) & CAAI TRIT 2023.
[Project]
[PDF]
[Code]
[BibTeX]
We embrace the ambiguity of the reconstruction and propose a multi-hypothesis approach, MH-HMR, to efficiently model the multi-hypothesis representation and build strong relationships among the hypothetical features.
|
|
High-fidelity Facial Avatar Reconstruction from Monocular Video with Generative Priors
Xiongzheng Li, Jing Huang, Jinsong Zhang, Xiaokun Sun, Haibiao Xuan, Yu-Kun Lai, Yingdi Xie, Jingyu Yang and Kun Li
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2022.
[Project]
[PDF]
[Code]
[BibTeX]
We propose the first method to allow everyone to easily reconstruct their own 3D inner-body under daily clothing from a self-captured video with the mean reconstruction error of 0.73cm within 15s.
|