A self-supervised point-cloud pretraining framework that replaces slow volume rendering with fast 3D Gaussian Splatting, matching downstream accuracy at roughly 9x lower pretraining cost.
3D semantic parsing of large-scale indoor spaces
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
-
Point Cloud Unsupervised Pre-training via 3D Gaussian Splatting
A self-supervised point-cloud pretraining framework that replaces slow volume rendering with fast 3D Gaussian Splatting, matching downstream accuracy at roughly 9x lower pretraining cost.