# Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras

arXiv: https://arxiv.org/abs/2503.17262 · HTML: https://mlsanity.com/paper/2503.17262/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 52 references that are in the map.
- First posted on arXiv 21 Mar 2025.

## Builds on (most cited first, 30 of 33)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [High Speed and High Dynamic Range Video with an Event Camera](https://mlsanity.com/paper/1906.07165/) (2019)
- [Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion](https://mlsanity.com/paper/1812.08156/) (2018)
- [DSEC: A Stereo Event Camera Dataset for Driving Scenarios](https://mlsanity.com/paper/2103.06011/) (2021)
- [EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Cameras](https://mlsanity.com/paper/1802.06898/) (2018)
- [End-to-End Learning of Representations for Asynchronous Event-Based Data](https://mlsanity.com/paper/1904.08245/) (2019)
- [The Event-Camera Dataset and Simulator: Event-based Data for Pose Estimation, Visual Odometry, and SLAM](https://mlsanity.com/paper/1610.08336/) (2016)
- [A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation](https://mlsanity.com/paper/1804.01306/) (2018)
- [E-RAFT: Dense Optical Flow from Event Cameras](https://mlsanity.com/paper/2108.10552/) (2021)
- [Event-based Moving Object Detection and Tracking](https://mlsanity.com/paper/1803.04523/) (2018)
- [Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy](https://mlsanity.com/paper/2009.08283/) (2020)
- [Time Lens++: Event-based Frame Interpolation with Parametric Non-linear Flow and Multi-scale Fusion](https://mlsanity.com/paper/2203.17191/) (2022)
- [Secrets of Event-Based Optical Flow](https://mlsanity.com/paper/2207.10022/) (2022)
- [Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks](https://mlsanity.com/paper/2302.08890/) (2023)
- [Focus Is All You Need: Loss Functions For Event-based Vision](https://mlsanity.com/paper/1904.07235/) (2019)
- [Continuous-time Intensity Estimation Using Event Cameras](https://mlsanity.com/paper/1811.00386/) (2018)
- [Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation](https://mlsanity.com/paper/1607.06283/) (2016)
- [Taming Contrast Maximization for Learning Sequential, Low-latency, Event-based Optical Flow](https://mlsanity.com/paper/2303.05214/) (2023)
- [Event Collapse in Contrast Maximization Frameworks](https://mlsanity.com/paper/2207.04007/) (2022)
- [BlinkFlow: A Dataset to Push the Limits of Event-based Optical Flow Estimation](https://mlsanity.com/paper/2303.07716/) (2023)
- [TMA: Temporal Motion Aggregation for Event-based Optical Flow](https://mlsanity.com/paper/2303.11629/) (2023)
- [Lightweight Event-based Optical Flow Estimation via Iterative Deblurring](https://mlsanity.com/paper/2211.13726/) (2022)
- [Real-Time Optical Flow for Vehicular Perception with Low- and High-Resolution Event Cameras](https://mlsanity.com/paper/2112.10591/) (2021)
- [Learning Optical Flow from Event Camera with Rendered Dataset](https://mlsanity.com/paper/2303.11011/) (2023)
- [EVREAL: Towards a Comprehensive Benchmark and Analysis Suite for Event-based Video Reconstruction](https://mlsanity.com/paper/2305.00434/) (2023)
- [Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation](https://mlsanity.com/paper/2407.10802/) (2024)
- [A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework](https://mlsanity.com/paper/2212.07350/) (2022)

## Built on by (most cited first, 10 of 10)

- [Simultaneous Motion And Noise Estimation with Event Cameras](https://mlsanity.com/paper/2504.04029/) (2025)
- [DERD-Net: Learning Depth from Event-based Ray Densities](https://mlsanity.com/paper/2504.15863/) (2025)
- [Learning Efficient Meshflow and Optical Flow from Event Cameras](https://mlsanity.com/paper/2510.04111/) (2025)
- [Fast Feature Field (F3): A Predictive Representation of Events](https://mlsanity.com/paper/2509.25146/) (2025)
- [Iterative Event-based Motion Segmentation by Variational Contrast Maximization](https://mlsanity.com/paper/2504.18447/) (2025)
- [x2-Fusion: Cross-Modality and Cross-Dimension Flow Estimation in Event Edge Space](https://mlsanity.com/paper/2603.16671/) (2026)
- [TETO: Tracking Events with Teacher Observation for Motion Estimation and Frame Interpolation](https://mlsanity.com/paper/2603.23487/) (2026)
- [From Contrast to Consistency: Rethinking Event-based Continuous-Time Optical Flow Estimation](https://mlsanity.com/paper/2605.25570/) (2026)
- [Geometric-Photometric Event-based 3D Gaussian Ray Tracing](https://mlsanity.com/paper/2512.18640/) (2025)
- [Interp3R: Continuous-time 3D Geometry Estimation with Frames and Events](https://mlsanity.com/paper/2603.14528/) (2026)

## Abstract (arXiv)

Event cameras rely on motion to obtain information about scene appearance. This means that appearance and motion are inherently linked: either both are present and recorded in the event data, or neither is captured. Previous works treat the recovery of these two visual quantities as separate tasks, which does not fit with the above-mentioned nature of event cameras and overlooks the inherent relations between them. We propose an unsupervised learning framework that jointly estimates optical flow (motion) and image intensity (appearance) using a single network. From the data generation model, we newly derive the event-based photometric error as a function of optical flow and image intensity. This error is further combined with the contrast maximization framework to form a comprehensive loss function that provides proper constraints for both flow and intensity estimation. Exhaustive experiments show our method's state-of-the-art performance: in optical flow estimation, it reduces EPE by 20% and AE by 25% compared to unsupervised approaches, while delivering competitive intensity estimation results, particularly in high dynamic range scenarios. Our method also achieves shorter inference time than all other optical flow methods and many of the image reconstruction methods, while they output only one quantity. Project page: https://github.com/tub-rip/E2FAI