COSMOS : coherent supergaussian modeling with spatial priors for sparse-view 3D splatting

다국어 초록 (Multilingual Abstract)

3D Gaussian Splatting (3DGS) has recently emerged as a promising approach for 3D reconstruction, providing explicit, point-based representations and enabling high-quality real time rendering. However, when trained with sparse input views, 3DGS suffers from overfitting and structural degradation, leading to poor generalization on novel views. This limitation arises from its optimization relying solely on photometric loss without incorporating any 3D structure priors.
To address this issue, we propose Coherent supergaussian Modeling with Spatial Priors (COSMOS). Inspired by the concept of superpoints from 3D segmentation, COSMOS introduces 3D structure priors by newly defining supergaussian groupings of Gaussians based on local geometric cues and appearance features. To this end, COSMOS applies inter group global self-attention across supergaussian groups and sparse local attention among individual Gaussians, enabling the integration of global and local spatial information. These structure-aware features are then used for predicting Gaussian attributes, facilitating more consistent 3D reconstructions. Furthermore, by leveraging supergaussian-based grouping, COSMOSenforcesanintra-grouppositional regularization to maintain structural coherence and suppress floaters, thereby enhancing training stability under sparse-view conditions. Our experiments on Blender and DTU show that COSMOS surpasses state-of-the-art methods in sparse-view settings without any external depth supervision.

목차 (Table of Contents)

• Chapter 1. Introduction 1
• Chapter 2. Related Work 5
• 1. Neural Representations for 3D reconstruction 5
• 2. Few-shot 3D reconstruction 6
• 3. Structured Group Representations 7
• Chapter 3. Methodology 10
• 1. Preliminaries for 3DGS 10
• 2. Supergaussian Grouping 11
• 3. Supergaussian Self-Attention 13
• 4. Supergaussian Position Regularization 15
• Chapter 4. Experiment 21
• 1. Setup 21
• 2. Comparison 22
• 3. Ablation Study 24
• 4. Limitation 25
• Chapter 5. Conclusion 26
• References 26
• Appendix 33