The reviewed record of science sign in
Pith

arxiv: 2409.04243 · v1 · pith:N4XEB7II · submitted 2024-09-06 · cs.CV

Hybrid Cost Volume for Memory-Efficient Optical Flow

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:N4XEB7IIrecord.jsonopen to challenge →

classification cs.CV
keywords costflowvolumeshcvflowmemory-efficientmethodsvolumelocal
0
0 comments X
read the original abstract

Current state-of-the-art flow methods are mostly based on dense all-pairs cost volumes. However, as image resolution increases, the computational and spatial complexity of constructing these cost volumes grows at a quartic rate, making these methods impractical for high-resolution images. In this paper, we propose a novel Hybrid Cost Volume for memory-efficient optical flow, named HCV. To construct HCV, we first propose a Top-k strategy to separate the 4D cost volume into two global 3D cost volumes. These volumes significantly reduce memory usage while retaining a substantial amount of matching information. We further introduce a local 4D cost volume with a local search space to supplement the local information for HCV. Based on HCV, we design a memory-efficient optical flow network, named HCVFlow. Compared to the recurrent flow methods based the all-pairs cost volumes, our HCVFlow significantly reduces memory consumption while ensuring high accuracy. We validate the effectiveness and efficiency of our method on the Sintel and KITTI datasets and real-world 4K (2160*3840) resolution images. Extensive experiments show that our HCVFlow has very low memory usage and outperforms other memory-efficient methods in terms of accuracy. The code is publicly available at https://github.com/gangweiX/HCVFlow.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.