Invaria trains point cloud encoders with next-resolution prediction to learn scale and density invariant features, yielding higher mIoU on ScanNet under lower resolution and scaled objects while using a smaller model.
Point transformer v2: Grouped vec- tor attention and partition-based pooling.Advances in Neural Information Processing Systems, 35:33330– 33342
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
-
Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction
Invaria trains point cloud encoders with next-resolution prediction to learn scale and density invariant features, yielding higher mIoU on ScanNet under lower resolution and scaled objects while using a smaller model.