no code implementations • 10 Apr 2024 • Tianxin Huang, Zhiwen Yan, Yuyang Zhao, Gim Hee Lee
3D point cloud completion is designed to recover complete shapes from partially observed point clouds.
no code implementations • 28 Nov 2023 • Zhiwen Yan, Weng Fei Low, Yu Chen, Gim Hee Lee
3D Gaussians have recently emerged as a highly efficient representation for 3D reconstruction and rendering.
no code implementations • 24 Nov 2023 • Yuyang Zhao, Zhiwen Yan, Enze Xie, Lanqing Hong, Zhenguo Li, Gim Hee Lee
We introduce Animate124 (Animate-one-image-to-4D), the first work to animate a single in-the-wild image into 3D video through textual motion descriptions, an underexplored problem with significant applications.
no code implementations • 24 May 2023 • Zhiwen Yan, Chen Li, Gim Hee Lee
Dynamic neural radiance fields (dynamic NeRFs) have demonstrated impressive results in novel view synthesis on 3D dynamic scenes.
1 code implementation • CVPR 2023 • Zhiwen Yan, Chen Li, Gim Hee Lee
We evaluate our model based on the novel view synthesis quality with a self-collected dataset of different moving specular objects in realistic environments.
1 code implementation • 23 Dec 2021 • Zhiwen Yan, Teck Khim Ng
Adversarial training, the process of training a deep learning model with adversarial data, is one of the most successful adversarial defense methods for deep learning models.