Efficient All-Pairs Correlation Volume Sampling for Optical Flow Estimation

Karlis Martins Briedis, Studios, ETH Zurich 0000-0003-4012-6292, Markus Gross, Studios, ETH Zurich 0009-0003-9324-779X, Christopher Schroers, Studios 0000-0003-1473-1878; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026, pp. 5700-5709

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.