# Imposing Consistency for Optical Flow Estimation

arXiv: https://arxiv.org/abs/2204.07262 · HTML: https://mlsanity.com/paper/2204.07262/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 52 references that are in the map.
- First posted on arXiv 14 Apr 2022.

## Builds on (most cited first, 30 of 36)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (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)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Optical Flow Estimation using a Spatial Pyramid Network](https://mlsanity.com/paper/1611.00850/) (2016)
- [S4L: Self-Supervised Semi-Supervised Learning](https://mlsanity.com/paper/1905.03670/) (2019)
- [DVC: An End-to-end Deep Video Compression Framework](https://mlsanity.com/paper/1812.00101/) (2018)
- [Learning Correspondence from the Cycle-Consistency of Time](https://mlsanity.com/paper/1903.07593/) (2019)
- [Learning to Estimate Hidden Motions with Global Motion Aggregation](https://mlsanity.com/paper/2104.02409/) (2021)
- [UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss](https://mlsanity.com/paper/1711.07837/) (2017)
- [Video Compression through Image Interpolation](https://mlsanity.com/paper/1804.06919/) (2018)
- [Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation](https://mlsanity.com/paper/1904.05290/) (2019)
- [SelFlow: Self-Supervised Learning of Optical Flow](https://mlsanity.com/paper/1904.09117/) (2019)
- [What Matters in Unsupervised Optical Flow](https://mlsanity.com/paper/2006.04902/) (2020)
- [MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask](https://mlsanity.com/paper/2003.10955/) (2020)
- [AutoFlow: Learning a Better Training Set for Optical Flow](https://mlsanity.com/paper/2104.14544/) (2021)
- [Occlusion Aware Unsupervised Learning of Optical Flow](https://mlsanity.com/paper/1711.05890/) (2017)
- [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)
- [DeepTAM: Deep Tracking and Mapping](https://mlsanity.com/paper/1808.01900/) (2018)
- [A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization](https://mlsanity.com/paper/1903.07414/) (2019)
- [DDFlow: Learning Optical Flow with Unlabeled Data Distillation](https://mlsanity.com/paper/1902.09145/) (2019)
- [Interpolation-based semi-supervised learning for object detection](https://mlsanity.com/paper/2006.02158/) (2020)
- [Milking CowMask for Semi-Supervised Image Classification](https://mlsanity.com/paper/2003.12022/) (2020)

## Built on by (most cited first, 24 of 24)

- [The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation](https://mlsanity.com/paper/2306.01923/) (2023)
- [Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable Categories](https://mlsanity.com/paper/2211.03889/) (2022)
- [MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation](https://mlsanity.com/paper/2307.14336/) (2023)
- [GAFlow: Incorporating Gaussian Attention into Optical Flow](https://mlsanity.com/paper/2309.16217/) (2023)
- [Boosting Object Representation Learning via Motion and Object Continuity](https://mlsanity.com/paper/2211.09771/) (2022)
- [AnyFlow: Arbitrary Scale Optical Flow with Implicit Neural Representation](https://mlsanity.com/paper/2303.16493/) (2023)
- [CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoning](https://mlsanity.com/paper/2311.02661/) (2023)
- [DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling](https://mlsanity.com/paper/2303.14078/) (2023)
- [Refining Pre-Trained Motion Models](https://mlsanity.com/paper/2401.00850/) (2024)
- [OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation](https://mlsanity.com/paper/2403.18092/) (2024)
- [Optical Flow for Autonomous Driving: Applications, Challenges and Improvements](https://mlsanity.com/paper/2301.04422/) (2023)
- [DIFT: Dynamic Iterative Field Transforms for Memory Efficient Optical Flow](https://mlsanity.com/paper/2306.05691/) (2023)
- [FocusFlow: Boosting Key-Points Optical Flow Estimation for Autonomous Driving](https://mlsanity.com/paper/2308.07104/) (2023)
- [CLIP-FLow: Contrastive Learning by semi-supervised Iterative Pseudo labeling for Optical Flow Estimation](https://mlsanity.com/paper/2210.14383/) (2022)
- [SciFlow: Empowering Lightweight Optical Flow Models with Self-Cleaning Iterations](https://mlsanity.com/paper/2404.08135/) (2024)
- [YOIO: You Only Iterate Once by mining and fusing multiple necessary global information in the optical flow estimation](https://mlsanity.com/paper/2401.05879/) (2024)
- [Triangular Consistency as a Universal Constraint for Learning Optical Flow](https://mlsanity.com/paper/2606.19938/) (2026)
- [CGCV:Context Guided Correlation Volume for Optical Flow Neural Networks](https://mlsanity.com/paper/2212.10174/) (2022)
- [The Devil in the Details: Simple and Effective Optical Flow Synthetic Data Generation](https://mlsanity.com/paper/2308.07378/) (2023)
- [Dual-Stream Attention Transformers for Sewer Defect Classification](https://mlsanity.com/paper/2311.16145/) (2023)
- [Trustworthy Self-Attention: Enabling the Network to Focus Only on the Most Relevant References](https://mlsanity.com/paper/2403.00211/) (2024)
- [HMAFlow: Learning More Accurate Optical Flow via Hierarchical Motion Field Alignment](https://mlsanity.com/paper/2409.05531/) (2024)
- [Learning Optical Flow Field via Neural Ordinary Differential Equation](https://mlsanity.com/paper/2506.03290/) (2025)
- [SciFlow: Semantic Cross Interference for Self-Supervised Optical Flow Domain Generalization](https://mlsanity.com/paper/2606.29004/) (2026)

## Abstract (arXiv)

Imposing consistency through proxy tasks has been shown to enhance data-driven learning and enable self-supervision in various tasks. This paper introduces novel and effective consistency strategies for optical flow estimation, a problem where labels from real-world data are very challenging to derive. More specifically, we propose occlusion consistency and zero forcing in the forms of self-supervised learning and transformation consistency in the form of semi-supervised learning. We apply these consistency techniques in a way that the network model learns to describe pixel-level motions better while requiring no additional annotations. We demonstrate that our consistency strategies applied to a strong baseline network model using the original datasets and labels provide further improvements, attaining the state-of-the-art results on the KITTI-2015 scene flow benchmark in the non-stereo category. Our method achieves the best foreground accuracy (4.33% in Fl-all) over both the stereo and non-stereo categories, even though using only monocular image inputs.