{"ID":6023408,"CreatedAt":"2026-07-08T01:00:23.257252134Z","UpdatedAt":"2026-07-10T06:38:11.380144103Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.05906","arxiv_id":"2607.05906","title":"GaussFusion: Towards Multimodal 3D Gaussian Pretraining","abstract":"3D Gaussian Splatting provides an explicit representation that jointly models geometry and appearance, serving as a scalable foundation for 3D representation learning. Existing pre-training methods for Gaussian representations, such as masked Gaussian reconstruction, primarily capture local structures but offer limited semantic supervision. In this paper, we propose GaussFusion, a multimodal pre-training framework for 3D Gaussian representations. GaussFusion integrates image and text supervision into masked Gaussian modeling through cross-modal semantic alignment, enabling the Gaussian encoder to learn both visual and language-level semantic information during pre-training. To better adapt masked modeling to the non-uniform distribution of Gaussian primitives, we further propose Gaussian Salience-guided Multi-scale Hole Masking (GSHM). GSHM constructs spatially continuous masked regions based on Gaussian salience. By applying hole masks at multiple scales, GSHM encourages the encoder to capture both fine-grained local patterns and broader structural dependencies. Extensive experiments on downstream tasks demonstrate that GaussFusion improves the transferability of Gaussian representations. Notably, GaussFusion outperforms Gaussian-MAE on ModelNet40 and ScanObjectNN (PB-T50-RS) by 0.61\\% and 3.85\\%, respectively.","short_abstract":"3D Gaussian Splatting provides an explicit representation that jointly models geometry and appearance, serving as a scalable foundation for 3D representation learning. Existing pre-training methods for Gaussian representations, such as masked Gaussian reconstruction, primarily capture local structures but offer limited...","url_abs":"https://arxiv.org/abs/2607.05906","url_pdf":"https://arxiv.org/pdf/2607.05906v1","authors":"[\"Zhixuan You\",\"Jihua Zhu\",\"Yiding Sun\",\"Zihao Guo\",\"Haozhe Cheng\",\"Dongxu Zhang\",\"Lin Chen\",\"Hainan Luo\"]","published":"2026-07-07T07:01:46Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}