# Optical Flow Estimation in the Deep Learning Age

arXiv: https://arxiv.org/abs/2004.02853 · HTML: https://mlsanity.com/paper/2004.02853/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2020.

## Built on by (most cited first, 13 of 13)

- [Learning Accurate Dense Correspondences and When to Trust Them](https://mlsanity.com/paper/2101.01710/) (2021)
- [PDC-Net+: Enhanced Probabilistic Dense Correspondence Network](https://mlsanity.com/paper/2109.13912/) (2021)
- [Learning Dense and Continuous Optical Flow from an Event Camera](https://mlsanity.com/paper/2211.09078/) (2022)
- [Edge-guided Multi-domain RGB-to-TIR image Translation for Training Vision Tasks with Challenging Labels](https://mlsanity.com/paper/2301.12689/) (2023)
- [Boosting Object Representation Learning via Motion and Object Continuity](https://mlsanity.com/paper/2211.09771/) (2022)
- [Deep DIC: Deep Learning-Based Digital Image Correlation for End-to-End Displacement and Strain Measurement](https://mlsanity.com/paper/2110.13720/) (2021)
- [Evaluating Machine Learning Models with NERO: Non-Equivariance Revealed on Orbits](https://mlsanity.com/paper/2305.19889/) (2023)
- [Scalable 3D Semantic Segmentation for Gun Detection in CT Scans](https://mlsanity.com/paper/2112.03917/) (2021)
- [A qualitative investigation of optical flow algorithms for video denoising](https://mlsanity.com/paper/2204.08791/) (2022)
- [Deep learning-based Visual Measurement Extraction within an Adaptive Digital Twin Framework from Limited Data Using Transfer Learning](https://mlsanity.com/paper/2410.05403/) (2024)
- [Investigation of Frame Differences as Motion Cues for Video Object Segmentation](https://mlsanity.com/paper/2503.09132/) (2025)
- [Bayes-DIC Net: Estimating Digital Image Correlation Uncertainty with Bayesian Neural Networks](https://mlsanity.com/paper/2512.04323/) (2025)
- [Deep learning enables urban change profiling through alignment of historical maps](https://mlsanity.com/paper/2602.02154/) (2026)

## Abstract (arXiv)

Akin to many subareas of computer vision, the recent advances in deep learning have also significantly influenced the literature on optical flow. Previously, the literature had been dominated by classical energy-based models, which formulate optical flow estimation as an energy minimization problem. However, as the practical benefits of Convolutional Neural Networks (CNNs) over conventional methods have become apparent in numerous areas of computer vision and beyond, they have also seen increased adoption in the context of motion estimation to the point where the current state of the art in terms of accuracy is set by CNN approaches. We first review this transition as well as the developments from early work to the current state of CNNs for optical flow estimation. Alongside, we discuss some of their technical details and compare them to recapitulate which technical contribution led to the most significant accuracy improvements. Then we provide an overview of the various optical flow approaches introduced in the deep learning age, including those based on alternative learning paradigms (e.g., unsupervised and semi-supervised methods) as well as the extension to the multi-frame case, which is able to yield further accuracy improvements.