# Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation

arXiv: https://arxiv.org/abs/1508.05151 · HTML: https://mlsanity.com/paper/1508.05151/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2015.

## Built on by (most cited first, 22 of 22)

- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [Global Matching with Overlapping Attention for Optical Flow Estimation](https://mlsanity.com/paper/2203.11335/) (2022)
- [Dense Optical Tracking: Connecting the Dots](https://mlsanity.com/paper/2312.00786/) (2023)
- [Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction](https://mlsanity.com/paper/2503.16318/) (2025)
- [MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation](https://mlsanity.com/paper/2211.06018/) (2022)
- [Rethinking RAFT for Efficient Optical Flow](https://mlsanity.com/paper/2401.00833/) (2024)
- [SplatFlow: Learning Multi-frame Optical Flow via Splatting](https://mlsanity.com/paper/2306.08887/) (2023)
- [FocusFlow: Boosting Key-Points Optical Flow Estimation for Autonomous Driving](https://mlsanity.com/paper/2308.07104/) (2023)
- [Target Detection and Segmentation in Circular-Scan Synthetic-Aperture-Sonar Images using Semi-Supervised Convolutional Encoder-Decoders](https://mlsanity.com/paper/2101.03603/) (2021)
- [Normalized Convolution Upsampling for Refined Optical Flow Estimation](https://mlsanity.com/paper/2102.06979/) (2021)
- [Attentive Multimodal Fusion for Optical and Scene Flow](https://mlsanity.com/paper/2307.15301/) (2023)
- [Towards Dependable Optical Flow: Benchmarks for Real-World Spatiotemporal Corruptions](https://mlsanity.com/paper/2411.14865/) (2024)
- [Fusing Frame and Event Vision for High-speed Optical Flow for Edge Application](https://mlsanity.com/paper/2207.10720/) (2022)
- [DnSwin: Toward Real-World Denoising via Continuous Wavelet Sliding-Transformer](https://mlsanity.com/paper/2207.13861/) (2022)
- [Segment Anything for Video: A Comprehensive Review of Video Object Segmentation and Tracking from Past to Future](https://mlsanity.com/paper/2507.22792/) (2025)
- [Triangular Consistency as a Universal Constraint for Learning Optical Flow](https://mlsanity.com/paper/2606.19938/) (2026)
- [Efficient data-driven encoding of scene motion using Eccentricity](https://mlsanity.com/paper/2103.02743/) (2021)
- [External-Memory Networks for Low-Shot Learning of Targets in Forward-Looking-Sonar Imagery](https://mlsanity.com/paper/2107.10504/) (2021)
- [FlowNAS: Neural Architecture Search for Optical Flow Estimation](https://mlsanity.com/paper/2207.01271/) (2022)
- [Learning Omnidirectional Flow in 360-degree Video via Siamese Representation](https://mlsanity.com/paper/2208.03620/) (2022)
- [Optical Flow Estimation in 360^circ Videos: Dataset, Model and Application](https://mlsanity.com/paper/2301.11880/) (2023)
- [Rethink Predicting the Optical Flow with the Kinetics Perspective](https://mlsanity.com/paper/2405.12512/) (2024)

## Abstract (arXiv)

Modern large displacement optical flow algorithms usually use an initialization by either sparse descriptor matching techniques or dense approximate nearest neighbor fields. While the latter have the advantage of being dense, they have the major disadvantage of being very outlier prone as they are not designed to find the optical flow, but the visually most similar correspondence. In this paper we present a dense correspondence field approach that is much less outlier prone and thus much better suited for optical flow estimation than approximate nearest neighbor fields. Our approach is conceptually novel as it does not require explicit regularization, smoothing (like median filtering) or a new data term, but solely our novel purely data based search strategy that finds most inliers (even for small objects), while it effectively avoids finding outliers. Moreover, we present novel enhancements for outlier filtering. We show that our approach is better suited for large displacement optical flow estimation than state-of-the-art descriptor matching techniques. We do so by initializing EpicFlow (so far the best method on MPI-Sintel) with our Flow Fields instead of their originally used state-of-the-art descriptor matching technique. We significantly outperform the original EpicFlow on MPI-Sintel, KITTI and Middlebury.