Relightable and Animatable Neural Avatars from Videos

no code implementations • 20 Dec 2023 • Wenbin Lin, Chengwei Zheng, Jun-Hai Yong, Feng Xu

To solve this ill-posed problem, we propose novel techniques to better model the geometry and shadow changes.

EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Points

no code implementations • CVPR 2023 • Chengwei Zheng, Wenbin Lin, Feng Xu

To achieve this, we propose a scene analysis method to detect and initialize key points by considering the dynamics in the scene, and a weighted key points strategy to model topologically varying dynamics by joint key points and weights optimization.

Novel View Synthesis

OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D Reconstruction

1 code implementation • CVPR 2022 • Wenbin Lin, Chengwei Zheng, Jun-Hai Yong, Feng Xu

In our technique, the motion of visible regions is first estimated and combined with temporal information to infer the motion of the occluded regions through an LSTM-involved graph neural network.

3D Reconstruction Motion Estimation