GaussFusion improves 3D Gaussian pre-training by adding image-text semantic alignment and a salience-guided multi-scale hole masking strategy, outperforming Gaussian-MAE on downstream 3D tasks.
Title resolution pending
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
-
GaussFusion: Towards Multimodal 3D Gaussian Pretraining
GaussFusion improves 3D Gaussian pre-training by adding image-text semantic alignment and a salience-guided multi-scale hole masking strategy, outperforming Gaussian-MAE on downstream 3D tasks.