Pointy, a lightweight transformer trained on 39k point clouds, outperforms larger foundation models trained on 200k+ samples and nears SOTA from million-sample multimodal models.
Ulip-2: Towards scala ble multimodal pre-training for 3d understanding
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pointy - A Lightweight Transformer for Point Cloud Foundation Models
Pointy, a lightweight transformer trained on 39k point clouds, outperforms larger foundation models trained on 200k+ samples and nears SOTA from million-sample multimodal models.