EBFA-6D: End-to-End Transparent Object 6D Pose Estimation Based on a Boundary Feature Augmented Mechanism
Xinbei Jiang, Zichen Zhu, Tianhan Gao, Nan Guo · 2024
Read EBFA-6D: End-to-End Transparent Object 6D Pose Estimation Based on a Boundary Feature Augmented Mechanism by Xinbei Jiang, Zichen Zhu, Tianhan Gao, Nan Guo (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11644825.txt.
Description
Jiang and co-authors tackle a hard vision problem: working out the exact position and orientation of transparent objects from a single photo. Glassware and clear plastic have little texture or color, and depth sensors often fail on them, yet robots still need to grasp them safely.
Their system, EBFA-6D, uses the strong outlines that transparent objects show at their edges. A boundary feature mechanism boosts those edge signals, and features are fused step by step to pin down location. On the ClearPose benchmark the method beat earlier approaches in accuracy while running close to real time. The authors present it as a practical step toward robots handling glass and clear packaging reliably.
Catalog record
| CREATOR | Xinbei Jiang, Zichen Zhu, Tianhan Gao, Nan Guo |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |