DRGSplat: Depth-Regularized 3D Gaussian Splatting
Abstract
3D Gaussian Splatting has rapidly become a leading method for photorealistic novel view synthesis. However, its geometric accuracy often lags behind its visual fidelity. Existing methods to improve geometry typically constrain the 3D Gaussians directly, compromising their volumetric nature.
We introduce DRGSplat, a novel depth-regularization approach for 3D Gaussian Splatting that enhances geometric accuracy without direct modifications of the Gaussian primitives. DRGSplat regularizes the rendered depth maps during training with three key losses: a monocular depth loss enforcing global consistency, a surface normal loss refining local detail, and a new uncertainty-aware flatness loss that selectively penalizes high-gradient regions while avoiding the gradient instabilities common to direct curvature constraints.
Experiments on standard benchmarks show that DRGSplat maintains the strong photometric quality of Gaussian Splatting while substantially improving geometric accuracy and outperforming state-of-the-art geometry-focused methods.
On the ETH3D dataset, DRGSplat improves reconstruction accuracy, completeness, and F1 scores by 13, 25, and 16 percentage points, respectively. The code will be made publicly available.
We introduce DRGSplat, a novel depth-regularization approach for 3D Gaussian Splatting that enhances geometric accuracy without direct modifications of the Gaussian primitives. DRGSplat regularizes the rendered depth maps during training with three key losses: a monocular depth loss enforcing global consistency, a surface normal loss refining local detail, and a new uncertainty-aware flatness loss that selectively penalizes high-gradient regions while avoiding the gradient instabilities common to direct curvature constraints.
Experiments on standard benchmarks show that DRGSplat maintains the strong photometric quality of Gaussian Splatting while substantially improving geometric accuracy and outperforming state-of-the-art geometry-focused methods.
On the ETH3D dataset, DRGSplat improves reconstruction accuracy, completeness, and F1 scores by 13, 25, and 16 percentage points, respectively. The code will be made publicly available.
