Atsuhiro Noguchi
Papers
1
Total Citations
32
H-Index
1
About
Atsuhiro Noguchi is a leading researcher in computer vision and graphics, specializing in the 3D understanding and manipulation of articulated objects. His work centers on the unsupervised discovery of 3D joint structures, enabling the re-posing of objects like humans or animals without requiring manual annotation or pre-defined skeletons. His highly cited paper, "Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects" (2022, 32 citations), introduced a groundbreaking method that learns an object’s underlying joint hierarchy directly from video, allowing for realistic pose control in applications such as virtual reality and animation. This contribution addresses a critical bottleneck in 3D content creation, where understanding how parts move relative to each other is essential. Noguchi’s research has significant implications for film, gaming, and robotics, offering a scalable way to animate diverse articulated objects. His work stands out for its elegance in combining neural rendering with unsupervised learning, making him a rising figure in the field.
Research Focus
Key Achievements
Top Papers
- 1