PointTPA uses serialization-based neighborhood grouping and a dynamic parameter projector to adapt network weights per scene patch, reaching 78.4% mIoU on ScanNet with under 2% added parameters.
Point cloud mixture-of-domain- experts model for 3d self-supervised learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PointTPA: Dynamic Network Parameter Adaptation for 3D Scene Understanding
PointTPA uses serialization-based neighborhood grouping and a dynamic parameter projector to adapt network weights per scene patch, reaching 78.4% mIoU on ScanNet with under 2% added parameters.