CDGS: Confidence-Aware Depth Regularization for 3D Gaussian Splatting

TL;DR

This paper introduces CDGS, a confidence-aware depth regularization method that improves geometric accuracy and stability in 3D Gaussian Splatting for view synthesis, using multi-cue depth confidence maps.

Contribution

It develops a novel depth regularization approach leveraging confidence maps from monocular and SfM depths to enhance 3D Gaussian Splatting.

Findings

Improves geometric detail preservation during early training stages.

Achieves up to 2.31 dB higher PSNR in NVS tasks.

Reaches comparable F-scores with half the training iterations.

Abstract

3D Gaussian Splatting (3DGS) has shown significant advantages in novel view synthesis (NVS), particularly in achieving high rendering speeds and high-quality results. However, its geometric accuracy in 3D reconstruction remains limited due to the lack of explicit geometric constraints during optimization. This paper introduces CDGS, a confidence-aware depth regularization approach developed to enhance 3DGS. We leverage multi-cue confidence maps of monocular depth estimation and sparse Structure-from-Motion depth to adaptively adjust depth supervision during the optimization process. Our method demonstrates improved geometric detail preservation in early training stages and achieves competitive performance in both NVS quality and geometric accuracy. Experiments on the publicly available Tanks and Temples benchmark dataset show that our method achieves more stable convergence behavior and more accurate geometric reconstruction results, with improvements of up to 2.31 dB in PSNR for NVS and consistently lower geometric errors in M3C2 distance metrics. Notably, our method reaches comparable F-scores to the original 3DGS with only 50% of the training iterations. We expect this work will facilitate the development of efficient and accurate 3D reconstruction systems for real-world applications such as digital twin creation, heritage preservation, or forestry applications.