TriaGS: Differentiable Triangulation-Guided Geometric Consistency for 3D Gaussian Splatting

TL;DR

This paper introduces TriaGS, a method that enhances 3D Gaussian Splatting by enforcing geometric consistency through differentiable multi-view triangulation, leading to more accurate and high-fidelity 3D reconstructions.

Contribution

It proposes a novel differentiable triangulation-guided approach to improve 3D Gaussian Splatting reconstruction quality by enforcing global geometric consistency.

Findings

Achieves state-of-the-art results on DTU dataset with 0.50 mm Chamfer Distance.

Effectively reduces artifacts and unstructured geometry in reconstructions.

Demonstrates improved 3D surface fidelity across multiple datasets.

Abstract

3D Gaussian Splatting is crucial for real-time novel view synthesis due to its efficiency and ability to render photorealistic images. However, building a 3D Gaussian is guided solely by photometric loss, which can result in inconsistencies in reconstruction. This under-constrained process often results in "floater" artifacts and unstructured geometry, preventing the extraction of high-fidelity surfaces. To address this issue, our paper introduces a novel method that improves reconstruction by enforcing global geometry consistency through constrained multi-view triangulation. Our approach aims to achieve a consensus on 3D representation in the physical world by utilizing various estimated views. We optimize this process by penalizing the deviation of a rendered 3D point from a robust consensus point, which is re-triangulated from a bundle of neighboring views in a self-supervised fashion. We demonstrate the effectiveness of our method across multiple datasets, achieving state-of-the-art results. On the DTU dataset, our method attains a mean Chamfer Distance of 0.50 mm, outperforming comparable explicit methods. We will make our code open-source to facilitate community validation and ensure reproducibility.