MMPT combines three existing self-supervised tasks for point cloud pre-training and reports improved results across several benchmarks.
We fine-tune our model on the point cloud completion benchmarks for 200 epochs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding
MMPT combines three existing self-supervised tasks for point cloud pre-training and reports improved results across several benchmarks.