ZipMVS compresses cost volumes for memory-efficient multi-view stereo reconstruction

zhenjun_zhao · x · 2026-09-05

ZipMVS is a multi-view stereo method designed for efficient high-quality 3D reconstruction. A novel depth-hypothesis strategy — adjusting depth sampling ranges and deriving hypotheses from spatial cues — substantially compresses the cost volume, greatly reducing GPU memory while preserving accuracy. On DTU and Tanks and Temples it matches other efficiency-oriented MVS methods, balancing quality and memory. Code is available.

Original post →

More from Research

Research channel →