# A Fusion Approach for Multi-Frame Optical Flow Estimation

arXiv: https://arxiv.org/abs/1810.10066 · HTML: https://mlsanity.com/paper/1810.10066/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2018.

## Built on by (most cited first, 30 of 37)

- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [Shape of Motion: 4D Reconstruction from a Single Video](https://mlsanity.com/paper/2407.13764/) (2024)
- [Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories](https://mlsanity.com/paper/2204.04153/) (2022)
- [Tracking Everything Everywhere All at Once](https://mlsanity.com/paper/2306.05422/) (2023)
- [SpatialTracker: Tracking Any 2D Pixels in 3D Space](https://mlsanity.com/paper/2404.04319/) (2024)
- [AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation](https://mlsanity.com/paper/2304.09790/) (2023)
- [VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation](https://mlsanity.com/paper/2303.08340/) (2023)
- [MFT: Long-Term Tracking of Every Pixel](https://mlsanity.com/paper/2305.12998/) (2023)
- [MemFlow: Optical Flow Estimation and Prediction with Memory](https://mlsanity.com/paper/2404.04808/) (2024)
- [Spatio-Temporal Recurrent Networks for Event-Based Optical Flow Estimation](https://mlsanity.com/paper/2109.04871/) (2021)
- [Dense Continuous-Time Optical Flow from Events and Frames](https://mlsanity.com/paper/2203.13674/) (2022)
- [Self-Supervised Multi-Frame Monocular Scene Flow](https://mlsanity.com/paper/2105.02216/) (2021)
- [AccFlow: Backward Accumulation for Long-Range Optical Flow](https://mlsanity.com/paper/2308.13133/) (2023)
- [Optical Flow Training under Limited Label Budget via Active Learning](https://mlsanity.com/paper/2203.05053/) (2022)
- [M-FUSE: Multi-frame Fusion for Scene Flow Estimation](https://mlsanity.com/paper/2207.05704/) (2022)
- [StreamFlow: Streamlined Multi-Frame Optical Flow Estimation for Video Sequences](https://mlsanity.com/paper/2311.17099/) (2023)
- [L4P: Towards Unified Low-Level 4D Vision Perception](https://mlsanity.com/paper/2502.13078/) (2025)
- [SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving](https://mlsanity.com/paper/2303.06209/) (2023)
- [Context-PIPs: Persistent Independent Particles Demands Spatial Context Features](https://mlsanity.com/paper/2306.02000/) (2023)
- [Deep 360^circ Optical Flow Estimation Based on Multi-Projection Fusion](https://mlsanity.com/paper/2208.00776/) (2022)
- [SplatFlow: Learning Multi-frame Optical Flow via Splatting](https://mlsanity.com/paper/2306.08887/) (2023)
- [MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation](https://mlsanity.com/paper/2506.23151/) (2025)
- [Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation](https://mlsanity.com/paper/2106.04195/) (2021)
- [Detail Preserving Residual Feature Pyramid Modules for Optical Flow](https://mlsanity.com/paper/2107.10990/) (2021)
- [Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2210.11237/) (2022)
- [Self-Supervised Multi-Frame Neural Scene Flow](https://mlsanity.com/paper/2403.16116/) (2024)
- [GG-SSMs: Graph-Generating State Space Models](https://mlsanity.com/paper/2412.12423/) (2024)
- [SSTM: Spatiotemporal Recurrent Transformers for Multi-frame Optical Flow Estimation](https://mlsanity.com/paper/2304.14418/) (2023)
- [CathFlow: Self-Supervised Segmentation of Catheters in Interventional Ultrasound Using Optical Flow and Transformers](https://mlsanity.com/paper/2403.14465/) (2024)
- [Perturbed State Space Feature Encoders for Optical Flow with Event Cameras](https://mlsanity.com/paper/2504.10669/) (2025)

## Abstract (arXiv)

To date, top-performing optical flow estimation methods only take pairs of consecutive frames into account. While elegant and appealing, the idea of using more than two frames has not yet produced state-of-the-art results. We present a simple, yet effective fusion approach for multi-frame optical flow that benefits from longer-term temporal cues. Our method first warps the optical flow from previous frames to the current, thereby yielding multiple plausible estimates. It then fuses the complementary information carried by these estimates into a new optical flow field. At the time of writing, our method ranks first among published results in the MPI Sintel and KITTI 2015 benchmarks. Our models will be available on https://github.com/NVlabs/PWC-Net.