EFECL: Feature encoding enhancement with contrastive learning for indoor 3D object detection
Abstract Good proposal initials are critical for 3D object detection applications. However, due to the significant geometry variation of indoor scenes, incomplete and noisy proposals are inevitable in most cases. Mining feature information among these “bad” proposals may mislead the detection. Contr...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-08-01
|
| Series: | Computational Visual Media |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s41095-023-0366-0 |