DC4GS: Directional Consistency-Driven Adaptive Density Control for 3D Gaussian Splatting

TL;DR

This paper introduces DC4GS, a novel adaptive density control method for 3D Gaussian Splatting that uses directional consistency to improve structural accuracy and reduce primitive count, leading to better reconstruction fidelity.

Contribution

The paper proposes a new directional consistency-driven adaptive density control method that incorporates gradient angular coherence for more efficient 3D Gaussian Splatting.

Findings

Reduces the number of primitives by up to 30%.

Enhances reconstruction fidelity significantly.

Better captures local structural complexities.

Abstract

We present a Directional Consistency (DC)-driven Adaptive Density Control (ADC) for 3D Gaussian Splatting (DC4GS). Whereas the conventional ADC bases its primitive splitting on the magnitudes of positional gradients, we further incorporate the DC of the gradients into ADC, and realize it through the angular coherence of the gradients. Our DC better captures local structural complexities in ADC, avoiding redundant splitting. When splitting is required, we again utilize the DC to define optimal split positions so that sub-primitives best align with the local structures than the conventional random placement. As a consequence, our DC4GS greatly reduces the number of primitives (up to 30% in our experiments) than the existing ADC, and also enhances reconstruction fidelity greatly.