DET-GS: Depth- and Edge-Aware Regularization for High-Fidelity 3D Gaussian Splatting

TL;DR

DET-GS introduces a unified depth and edge-aware regularization framework that significantly improves geometric accuracy and visual fidelity in 3D Gaussian Splatting, especially under sparse-view conditions.

Contribution

It proposes a hierarchical geometric depth supervision and edge-aware regularization techniques to enhance structural fidelity and boundary preservation in 3D Gaussian Splatting.

Findings

Outperforms state-of-the-art methods on sparse-view benchmarks.

Enhances geometric accuracy and visual fidelity.

Robust against depth estimation noise.

Abstract

3D Gaussian Splatting (3DGS) represents a significant advancement in the field of efficient and high-fidelity novel view synthesis. Despite recent progress, achieving accurate geometric reconstruction under sparse-view conditions remains a fundamental challenge. Existing methods often rely on non-local depth regularization, which fails to capture fine-grained structures and is highly sensitive to depth estimation noise. Furthermore, traditional smoothing methods neglect semantic boundaries and indiscriminately degrade essential edges and textures, consequently limiting the overall quality of reconstruction. In this work, we propose DET-GS, a unified depth and edge-aware regularization framework for 3D Gaussian Splatting. DET-GS introduces a hierarchical geometric depth supervision framework that adaptively enforces multi-level geometric consistency, significantly enhancing structural fidelity and robustness against depth estimation noise. To preserve scene boundaries, we design an edge-aware depth regularization guided by semantic masks derived from Canny edge detection. Furthermore, we introduce an RGB-guided edge-preserving Total Variation loss that selectively smooths homogeneous regions while rigorously retaining high-frequency details and textures. Extensive experiments demonstrate that DET-GS achieves substantial improvements in both geometric accuracy and visual fidelity, outperforming state-of-the-art (SOTA) methods on sparse-view novel view synthesis benchmarks.