# Memory-Efficient Optical Flow via Radius-Distribution Orthogonal Cost Volume

arXiv: https://arxiv.org/abs/2312.03790 · HTML: https://mlsanity.com/paper/2312.03790/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 56 references that are in the map.
- First posted on arXiv 6 Dec 2023.

## Builds on (most cited first, 30 of 42)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation](https://mlsanity.com/paper/2003.07853/) (2020)
- [FlowFormer: A Transformer Architecture for Optical Flow](https://mlsanity.com/paper/2203.16194/) (2022)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [Learning to Estimate Hidden Motions with Global Motion Aggregation](https://mlsanity.com/paper/2104.02409/) (2021)
- [Iterative Geometry Encoding Volume for Stereo Matching](https://mlsanity.com/paper/2303.06615/) (2023)
- [Self-supervised Video Object Segmentation by Motion Grouping](https://mlsanity.com/paper/2104.07658/) (2021)
- [Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation](https://mlsanity.com/paper/1904.05290/) (2019)
- [Attention Concatenation Volume for Accurate and Efficient Stereo Matching](https://mlsanity.com/paper/2203.02146/) (2022)
- [MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask](https://mlsanity.com/paper/2003.10955/) (2020)
- [FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation](https://mlsanity.com/paper/2303.01237/) (2023)
- [The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation](https://mlsanity.com/paper/1905.00737/) (2019)
- [Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation](https://mlsanity.com/paper/1809.05571/) (2018)
- [Hierarchical Discrete Distribution Decomposition for Match Density Estimation](https://mlsanity.com/paper/1812.06264/) (2018)
- [Actor-Centric Relation Network](https://mlsanity.com/paper/1807.10982/) (2018)
- [CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow](https://mlsanity.com/paper/2203.16896/) (2022)
- [VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation](https://mlsanity.com/paper/2303.08340/) (2023)
- [A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization](https://mlsanity.com/paper/1903.07414/) (2019)
- [Global Matching with Overlapping Attention for Optical Flow Estimation](https://mlsanity.com/paper/2203.11335/) (2022)

## Built on by (most cited first, 9 of 9)

- [Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching](https://mlsanity.com/paper/2403.00486/) (2024)
- [WAFT: Warping-Alone Field Transforms for Optical Flow](https://mlsanity.com/paper/2506.21526/) (2025)
- [HDRFlow: Real-Time HDR Video Reconstruction with Large Motions](https://mlsanity.com/paper/2403.03447/) (2024)
- [BANet: Bilateral Aggregation Network for Mobile Stereo Matching](https://mlsanity.com/paper/2503.03259/) (2025)
- [MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation](https://mlsanity.com/paper/2506.23151/) (2025)
- [Hybrid Cost Volume for Memory-Efficient Optical Flow](https://mlsanity.com/paper/2409.04243/) (2024)
- [MegaFlow: Zero-Shot Large Displacement Optical Flow](https://mlsanity.com/paper/2603.25739/) (2026)
- [Multi-dimension Transformer with Attention-based Filtering for Medical Image Segmentation](https://mlsanity.com/paper/2405.12328/) (2024)
- [BAT: Learning Event-based Optical Flow with Bidirectional Adaptive Temporal Correlation](https://mlsanity.com/paper/2503.03256/) (2025)

## Abstract (arXiv)

The full 4D cost volume in Recurrent All-Pairs Field Transforms (RAFT) or global matching by Transformer achieves impressive performance for optical flow estimation. However, their memory consumption increases quadratically with input resolution, rendering them impractical for high-resolution images. In this paper, we present MeFlow, a novel memory-efficient method for high-resolution optical flow estimation. The key of MeFlow is a recurrent local orthogonal cost volume representation, which decomposes the 2D search space dynamically into two 1D orthogonal spaces, enabling our method to scale effectively to very high-resolution inputs. To preserve essential information in the orthogonal space, we utilize self attention to propagate feature information from the 2D space to the orthogonal space. We further propose a radius-distribution multi-scale lookup strategy to model the correspondences of large displacements at a negligible cost. We verify the efficiency and effectiveness of our method on the challenging Sintel and KITTI benchmarks, and real-world 4K (2160!×!3840) images. Our method achieves competitive performance on both Sintel and KITTI benchmarks, while maintaining the highest memory efficiency on high-resolution inputs.