Detection Based Part-level Articulated Object Reconstruction from Single RGBD Image
–Neural Information Processing Systems
We propose an end-to-end trainable, cross-category method for reconstructing multiple man-made articulated objects from a single RGBD image, focusing on part-level shape reconstruction and pose and kinematics estimation.
Neural Information Processing Systems
Feb-10-2026, 13:29:32 GMT
- Country:
- Asia > Japan > Honshū
- Chūbu > Ishikawa Prefecture
- Kanazawa (0.04)
- Kantō > Tokyo Metropolis Prefecture
- Tokyo (0.04)
- Chūbu > Ishikawa Prefecture
- Asia > Japan > Honshū
- Genre:
- Research Report (0.46)
- Technology:
- Information Technology
- Artificial Intelligence
- Machine Learning > Neural Networks
- Deep Learning (0.46)
- Representation & Reasoning (0.67)
- Robots (0.68)
- Vision (1.00)
- Machine Learning > Neural Networks
- Graphics (0.68)
- Artificial Intelligence
- Information Technology