Lune

NeurIPS2025顶会

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

Moonsoo Jeong, Dongbeen Kim, Minseong Kim, Sungkil Lee

2025年份
3被引次数

摘要

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. AbsGS AbsGS + DC4GS (Ours) D-SSIM: 0.173 D-SSIM: 0.163 Iteration Primitive count 800 K -1000 K -1200 K -1300 K -1500 K -1700 K -Ground Truth (GT)

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。

可以从这些问题问起

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始,无需绑卡

它引用的顶会 Paper21

相关 Paper

黄昏的海面,两侧是细线勾勒的悬崖