# Devon: Deformable Volume Network for Learning Optical Flow

arXiv: https://arxiv.org/abs/1802.07351 · HTML: https://mlsanity.com/paper/1802.07351/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2018.

## Built on by (most cited first, 16 of 16)

- [Learning to Estimate Hidden Motions with Global Motion Aggregation](https://mlsanity.com/paper/2104.02409/) (2021)
- [High-Resolution Optical Flow from 1D Attention and Correlation](https://mlsanity.com/paper/2104.13918/) (2021)
- [Learning Optical Flow from a Few Matches](https://mlsanity.com/paper/2104.02166/) (2021)
- [Extreme Rotation Estimation using Dense Correlation Volumes](https://mlsanity.com/paper/2104.13530/) (2021)
- [A Unified Pyramid Recurrent Network for Video Frame Interpolation](https://mlsanity.com/paper/2211.03456/) (2022)
- [Lightweight Event-based Optical Flow Estimation via Iterative Deblurring](https://mlsanity.com/paper/2211.13726/) (2022)
- [CSFlow: Learning Optical Flow via Cross Strip Correlation for Autonomous Driving](https://mlsanity.com/paper/2202.00909/) (2022)
- [Data-Efficient Unsupervised Interpolation Without Any Intermediate Frame for 4D Medical Images](https://mlsanity.com/paper/2404.01464/) (2024)
- [Local Motion and Contrast Priors Driven Deep Network for Infrared Small Target Super-Resolution](https://mlsanity.com/paper/2201.01014/) (2022)
- [DCVNet: Dilated Cost Volume Networks for Fast Optical Flow](https://mlsanity.com/paper/2103.17271/) (2021)
- [ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video](https://mlsanity.com/paper/2407.09797/) (2024)
- [OAS-Net: Occlusion Aware Sampling Network for Accurate Optical Flow](https://mlsanity.com/paper/2102.00364/) (2021)
- [ES-Net: An Efficient Stereo Matching Network](https://mlsanity.com/paper/2103.03922/) (2021)
- [CGCV:Context Guided Correlation Volume for Optical Flow Neural Networks](https://mlsanity.com/paper/2212.10174/) (2022)
- [Rethink Predicting the Optical Flow with the Kinetics Perspective](https://mlsanity.com/paper/2405.12512/) (2024)
- [ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video](https://mlsanity.com/paper/2409.12202/) (2024)

## Abstract (arXiv)

State-of-the-art neural network models estimate large displacement optical flow in multi-resolution and use warping to propagate the estimation between two resolutions. Despite their impressive results, it is known that there are two problems with the approach. First, the multi-resolution estimation of optical flow fails in situations where small objects move fast. Second, warping creates artifacts when occlusion or dis-occlusion happens. In this paper, we propose a new neural network module, Deformable Cost Volume, which alleviates the two problems. Based on this module, we designed the Deformable Volume Network (Devon) which can estimate multi-scale optical flow in a single high resolution. Experiments show Devon is more suitable in handling small objects moving fast and achieves comparable results to the state-of-the-art methods in public benchmarks.