David Joseph Tan
Papers
3
Total Citations
42
H-Index
3
About
David Joseph Tan is a computer vision researcher whose work spans 3D reconstruction, object pose estimation, and the intersection of deep learning with spatial understanding. He has made notable contributions to the challenging problem of recovering shape, pose, and appearance from single images, most prominently through his research on bootstrapped radiance field inversion, which couples Neural Radiance Fields (NeRF) with generative adversarial networks to enable robust 3D reconstruction even without exact ground-truth data — a significant step toward real-world applicability. This work has garnered 26 citations and represents a meaningful advance in monocular 3D understanding. Tan has also contributed to applied robotics and augmented reality, developing seamless algorithms for 6D object pose estimation using depth images that integrate object detection with temporal tracking — work that has earned 13 citations and demonstrates his ability to bridge theoretical vision research with practical deployment scenarios. Across his portfolio, Tan demonstrates a consistent focus on making spatial perception more accessible and accurate under constrained conditions, positioning him as a researcher whose contributions are increasingly relevant to robotics, AR, and embodied AI communities.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3