# High Resolution Multi-Scale RAFT (Robust Vision Challenge 2022)

arXiv: https://arxiv.org/abs/2210.16900 · HTML: https://mlsanity.com/paper/2210.16900/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 30 Oct 2022.

## Builds on (most cited first, 5 of 5)

- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [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)
- [Playing for Benchmarks](https://mlsanity.com/paper/1709.07322/) (2017)

## Built on by (most cited first, 12 of 12)

- [Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo](https://mlsanity.com/paper/2303.01943/) (2023)
- [CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow](https://mlsanity.com/paper/2211.10408/) (2022)
- [MemFlow: Optical Flow Estimation and Prediction with Memory](https://mlsanity.com/paper/2404.04808/) (2024)
- [CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoning](https://mlsanity.com/paper/2311.02661/) (2023)
- [Win-Win: Training High-Resolution Vision Transformers from Two Windows](https://mlsanity.com/paper/2310.00632/) (2023)
- [RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo](https://mlsanity.com/paper/2505.09368/) (2025)
- [PLT-D3: A High-fidelity Dynamic Driving Simulation Dataset for Stereo Depth and Scene Flow](https://mlsanity.com/paper/2406.07667/) (2024)
- [ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video](https://mlsanity.com/paper/2407.09797/) (2024)
- [Multispectral Stereo-Image Fusion for 3D Hyperspectral Scene Reconstruction](https://mlsanity.com/paper/2401.09428/) (2023)
- [ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video](https://mlsanity.com/paper/2409.12202/) (2024)
- [Local Attention Transformers for High-Detail Optical Flow Upsampling](https://mlsanity.com/paper/2412.06439/) (2024)
- [Motion-guided sparse correction enables expert-quality point tracking across diverse microscopy regimes](https://mlsanity.com/paper/2605.29220/) (2026)

## Abstract (arXiv)

In this report, we present our optical flow approach, MS-RAFT+, that won the Robust Vision Challenge 2022. It is based on the MS-RAFT method, which successfully integrates several multi-scale concepts into single-scale RAFT. Our approach extends this method by exploiting an additional finer scale for estimating the flow, which is made feasible by on-demand cost computation. This way, it can not only operate at half the original resolution, but also use MS-RAFT's shared convex upsampler to obtain full resolution flow. Moreover, our approach relies on an adjusted fine-tuning scheme during training. This in turn aims at improving the generalization across benchmarks. Among all participating methods in the Robust Vision Challenge, our approach ranks first on VIPER and second on KITTI, Sintel, and Middlebury, resulting in the first place of the overall ranking.