EnerGS: Energy-Based Gaussian Splatting with Partial Geometric Priors

TL;DR

EnerGS introduces a soft geometric guidance approach for 3D Gaussian Splatting, leveraging partial geometric priors as an energy field to enhance outdoor scene reconstruction quality and stability.

Contribution

It proposes a novel energy-based method that uses partial geometric priors as soft constraints, improving outdoor scene reconstruction without relying on complete geometric supervision.

Findings

Improves photometric quality in outdoor scene reconstructions.

Enhances geometric stability and reduces overfitting during training.

Effective in both sparse multi-view and monocular settings.

Abstract

3D Gaussian Splatting (3DGS) has been widely adopted for scene reconstruction, where training inherently constitutes a highly coupled and non-convex optimization problem. Recent works commonly incorporate geometric priors, such as LiDAR measurements, either for initialization or as training constraints, with the goal of improving photometric reconstruction quality. However, in large-scale outdoor scenarios, such geometric supervision is often spatially incomplete and uneven, which limits its effectiveness as a reliable prior and can even be detrimental to the final reconstruction. To address this challenge, we model partially observable geometry as a continuous energy field induced by geometric evidence and propose EnerGS. Rather than enforcing geometry as a hard constraint, EnerGS provides a soft geometric guidance for the optimization of Gaussian primitives, allowing geometric information to steer the optimization process without directly restricting the solution space. Extensive experiments on large-scale outdoor scenes demonstrate that, under both sparse multi-view and monocular settings, EnerGS consistently improves photometric quality and geometric stability, while effectively mitigating overfitting during 3DGS training.