# ScopeFlow: Dynamic Scene Scoping for Optical Flow

arXiv: https://arxiv.org/abs/2002.10770 · HTML: https://mlsanity.com/paper/2002.10770/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Feb 2020.

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

- [Learning to Estimate Hidden Motions with Global Motion Aggregation](https://mlsanity.com/paper/2104.02409/) (2021)
- [CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow](https://mlsanity.com/paper/2203.16896/) (2022)
- [Global Matching with Overlapping Attention for Optical Flow Estimation](https://mlsanity.com/paper/2203.11335/) (2022)
- [Learning Optical Flow from a Few Matches](https://mlsanity.com/paper/2104.02166/) (2021)
- [Synthetic Datasets for Autonomous Driving: A Survey](https://mlsanity.com/paper/2304.12205/) (2023)
- [DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow](https://mlsanity.com/paper/2204.00330/) (2022)
- [Learning Optical Flow with Adaptive Graph Reasoning](https://mlsanity.com/paper/2202.03857/) (2022)
- [Imposing Consistency for Optical Flow Estimation](https://mlsanity.com/paper/2204.07262/) (2022)
- [CSFlow: Learning Optical Flow via Cross Strip Correlation for Autonomous Driving](https://mlsanity.com/paper/2202.00909/) (2022)
- [CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoning](https://mlsanity.com/paper/2311.02661/) (2023)
- [MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation](https://mlsanity.com/paper/2211.06018/) (2022)
- [AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation](https://mlsanity.com/paper/2506.01061/) (2025)
- [SplatFlow: Learning Multi-frame Optical Flow via Splatting](https://mlsanity.com/paper/2306.08887/) (2023)
- [Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation](https://mlsanity.com/paper/2106.04195/) (2021)
- [Sensor-Guided Optical Flow](https://mlsanity.com/paper/2109.15321/) (2021)
- [Optical Flow Estimation via Motion Feature Recovery](https://mlsanity.com/paper/2101.06333/) (2021)
- [DCVNet: Dilated Cost Volume Networks for Fast Optical Flow](https://mlsanity.com/paper/2103.17271/) (2021)
- [Beyond a Video Frame Interpolator: A Space Decoupled Learning Approach to Continuous Image Transition](https://mlsanity.com/paper/2203.09771/) (2022)
- [Motion Estimation for Large Displacements and Deformations](https://mlsanity.com/paper/2206.12464/) (2022)
- [Deep-learning Optical Flow Outperforms PIV in Obtaining Velocity Fields from Active Nematics](https://mlsanity.com/paper/2404.15497/) (2024)
- [DESSERT: Diffusion-based Event-driven Single-frame Synthesis via Residual Training](https://mlsanity.com/paper/2512.17323/) (2025)
- [Optical Flow Dataset Synthesis from Unpaired Images](https://mlsanity.com/paper/2104.02615/) (2021)
- [Generating Superpixels for High-resolution Images with Decoupled Patch Calibration](https://mlsanity.com/paper/2108.08607/) (2021)
- [Motion-guided sparse correction enables expert-quality point tracking across diverse microscopy regimes](https://mlsanity.com/paper/2605.29220/) (2026)

## Abstract (arXiv)

We propose to modify the common training protocols of optical flow, leading to sizable accuracy improvements without adding to the computational complexity of the training process. The improvement is based on observing the bias in sampling challenging data that exists in the current training protocol, and improving the sampling process. In addition, we find that both regularization and augmentation should decrease during the training protocol. Using an existing low parameters architecture, the method is ranked first on the MPI Sintel benchmark among all other methods, improving the best two frames method accuracy by more than 10%. The method also surpasses all similar architecture variants by more than 12% and 19.7% on the KITTI benchmarks, achieving the lowest Average End-Point Error on KITTI2012 among two-frame methods, without using extra datasets.