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

Moonsoo Jeong, Dongbeen Kim, Minseong Kim, Sungkil Lee

Keywords: Computer Vision, Novel-View Synthesis, 3D Gaussian Splatting, Density Control, Directional Consistency

TL;DR: We introduce a directional consistency-driven adaptive density control for 3D Gaussian Splatting to guide split decisions and placements based on structural complexity, improving reconstruction fidelity with fewer primitives.

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.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 8673