LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS

于初见月

于 2024-10-11 14:00:00 发布

阅读量1k

点赞数 8

分类专栏： paper 文章标签：计算机视觉

本文链接：https://blog.csdn.net/weixin_44478317/article/details/142831154

版权

Abstract

Recent advancements in real-time neural rendering using point-based techniques have paved the way for the widespread adoption of 3D representations. However, foundational approaches like 3D Gaussian Splatting come with a substantial storage overhead caused by growing the SfM points to millions, often demanding gigabyte-level disk space for a single unbounded scene, posing significant scalability challenges and hindering the splatting efficiency.

To address this challenge, we introduce LightGaussian, a novel method designed to transform 3D Gaussians into a more efficient and compact format.

Drawing inspiration from the concept of Network Pruning, LightGaussian identifies Gaussians that are insignificant in contributing to the scene reconstruction and adopts a pruning and recovery process, effectively reducing redundancy in Gaussian counts while preserving visual effects.

受网络剪枝概念的启发，Light Gaussian识别对场景重建贡献不大的高斯，并采用剪枝和恢复过程，在保留视觉效果的同时有效地减少了高斯计数中的冗余。

Additionally, Ligh