Livox-3DMatch
- Citation Author(s):
-
Yibo Liu
(York University)
- Submitted by:
- Yibo Liu
- Last updated:
- DOI:
- 10.21227/vxhx-4a06
- Data Format:
457 views
- Categories:
- Keywords:
Abstract
Livox-3DMatch contains 11 scenes with 33 scans. Livox-3DMatch augments the original 3DMatch training data from 14,400 pairs to 17,700 pairs (a 22.91% increase). By training on this augmented dataset, the performance of the SOTA learning-based method SGHR is improved by 2.90% on 3DMatch,4.29% on ETH, and 22.72% (translation) / 11.19% (rotation) on ScanNet.
Instructions:
A detailed introduction is available in our GitHub repository: https://github.com/yorklyb/L-PR
