COSMOS: Coherent Supergaussian Modeling with Spatial Priors for Sparse-View 3D Splatting

TL;DR

COSMOS introduces a structure-aware supergaussian modeling approach with spatial priors to improve sparse-view 3D reconstruction, achieving better generalization and structural coherence.

Contribution

The paper proposes COSMOS, a novel method that incorporates 3D structure priors via supergaussian groupings and attention mechanisms for enhanced sparse-view 3D splatting.

Findings

Outperforms state-of-the-art in sparse-view 3D reconstruction

Enhances structural coherence and reduces floaters

No external depth supervision needed

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, COSMOS enforces an intra-group positional 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.