DALI improves unsupervised LiDAR 3D object detection across datasets by correcting pseudo label size bias via post-training scaling and by generating ray-constrained and constraint-free pseudo point clouds from 3D models.
Sparse fuse dense: Towards high quality 3d detection with depth completion,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DALI: Domain Adaptive LiDAR Object Detection via Distribution-level and Instance-level Pseudo Label Denoising
DALI improves unsupervised LiDAR 3D object detection across datasets by correcting pseudo label size bias via post-training scaling and by generating ray-constrained and constraint-free pseudo point clouds from 3D models.