Efficient All-Pairs Correlation Volume Sampling for Optical Flow Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Briedis, Karlis Martins, Gross, Markus, Schroers, Christopher
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917534966480896
author Briedis, Karlis Martins
Gross, Markus
Schroers, Christopher
author_facet Briedis, Karlis Martins
Gross, Markus
Schroers, Christopher
contents Recent optical flow estimation methods often employ local cost sampling from a dense all-pairs correlation volume. This results in quadratic computational and memory complexity in the number of pixels. Although an alternative memory-efficient implementation with on-demand cost computation exists, this is significantly slower in practice and therefore many prior methods process images at downsampled resolutions, missing fine-grained details. To address this, we propose an algorithm for both memory and compute-efficient implementation of the all-pairs correlation volume sampling, still matching the exact mathematical operator as defined by RAFT. Our approach outperforms on-demand sampling by up to 92% while maintaining equally low memory usage, and performs at least on par with the default implementation with up to 99% lower memory usage. As cost sampling makes up a significant portion of the overall runtime, this can translate to up to 63% savings for the total end-to-end model inference on high-resolution inputs. Our evaluation of existing methods includes an 8K ultra-high-resolution dataset and an inference-time extension of the SEA-RAFT method. With this, we achieve state-of-the-art results at high resolutions both in accuracy and runtime.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16942
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient All-Pairs Correlation Volume Sampling for Optical Flow Estimation
Briedis, Karlis Martins
Gross, Markus
Schroers, Christopher
Computer Vision and Pattern Recognition
Machine Learning
Recent optical flow estimation methods often employ local cost sampling from a dense all-pairs correlation volume. This results in quadratic computational and memory complexity in the number of pixels. Although an alternative memory-efficient implementation with on-demand cost computation exists, this is significantly slower in practice and therefore many prior methods process images at downsampled resolutions, missing fine-grained details. To address this, we propose an algorithm for both memory and compute-efficient implementation of the all-pairs correlation volume sampling, still matching the exact mathematical operator as defined by RAFT. Our approach outperforms on-demand sampling by up to 92% while maintaining equally low memory usage, and performs at least on par with the default implementation with up to 99% lower memory usage. As cost sampling makes up a significant portion of the overall runtime, this can translate to up to 63% savings for the total end-to-end model inference on high-resolution inputs. Our evaluation of existing methods includes an 8K ultra-high-resolution dataset and an inference-time extension of the SEA-RAFT method. With this, we achieve state-of-the-art results at high resolutions both in accuracy and runtime.
title Efficient All-Pairs Correlation Volume Sampling for Optical Flow Estimation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2505.16942