Wei‐Cheng Tseng
Papers
1
Total Citations
33
H-Index
1
About
Wei-Cheng Tseng is a leading researcher in computer vision and 3D scene understanding, with a focus on neural radiance fields and articulated object modeling. His most influential work, **CLA-NeRF** (Category-Level Articulated Neural Radiance Field), introduced a groundbreaking framework that unifies view synthesis, part segmentation, and articulated pose estimation for object categories—all without requiring CAD models or depth data. This innovation, which has garnered 33 citations since 2022, enables machines to reason about the structure and motion of articulated objects (e.g., cabinets, doors) from only RGB images with known camera poses. By training at the category level, Tseng’s approach significantly advances generalization in 3D perception, reducing reliance on expensive 3D annotations. His contributions are pivotal for applications in robotics, augmented reality, and autonomous systems, where understanding dynamic, articulated environments is critical. Tseng’s work exemplifies how neural radiance fields can be extended beyond static scenes to capture functional object properties, marking a key step toward more intelligent and adaptable visual AI.
Research Focus
Key Achievements
Top Papers
- 1CLA-NeRF: Category-Level Articulated Neural Radiance Field33 citations · 2022