ZipMVS: Multi-View Stereo with Compressed Cost Volumes

2026-08-28

AI Summary

ZipMVS通过创新的深度假设策略压缩成本体积，解决了多视图立体视觉方法内存需求大的问题，实现了高效高质量的3D重建。

Abstract

Multi-view stereo (MVS) methods typically deliver highly accurate 3D reconstructions from multiple registered RGB images, thanks to the highly informative, geometric constraints between them. However, their substantial memory requirements remain a major obstacle for deployment in domains such as aerospace and autonomous systems, where resource efficiency is critical. In this work, we introduce ZipMVS, an MVS method specifically designed for efficient high-quality reconstruction. We propose a novel depth-hypothesis strategy that enables substantial compression of the cost volume, hence greatly reducing GPU memory consumption while preserving reconstruction accuracy. Experiments on the DTU and Tanks and Temples datasets show that ZipMVS achieves competitive reconstruction quality compared with other efficiency-oriented MVS methods, while achieving a competitive balance between reconstruction quality and GPU memory usage. The code is available at https://github.com/JihnGlyn/ZipMVS

Problem

• Multi-View Stereo
• Memory Requirements
• Resource Efficiency

Innovation

• compressed cost volumes
• depth-hypothesis strategy
• GPU memory consumption