Skip to content

Opening book details…

About this document

Cascade Cost Volume For High-Resolution Multi-View Stereo and Stereo Matching by Arunabh Sharma is a document available to read on EtoBox.

The paper introduces a novel cascade cost volume formulation for high-resolution multi-view stereo and stereo matching, aimed at improving memory and time efficiency. By utilizing a feature pyramid and adaptive depth sampling, the proposed method significantly enhances reconstruction accuracy while reducing GPU memory usage and run-time. The approach demonstrates state-of-the-art performance on benchmark datasets, outperforming existing methods in both accuracy and efficiency.

Author
Arunabh Sharma
Language
EN