Imposing Consistency for Optical Flow Estimation
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3171-3181
Abstract
Imposing consistency through proxy tasks has been shown to enhance data-driven learning and enable self-supervision in various tasks. This paper introduces novel and effective consistency strategies for optical flow estimation, a problem where labels from real-world data are very challenging to derive. More specifically, we propose occlusion consistency and zero forcing in the forms of self-supervised learning and transformation consistency in the form of semi-supervised learning. We apply these consistency techniques in a way that the network model learns to describe pixel-level motions better while requiring no additional annotations. We demonstrate that our consistency strategies applied to a strong baseline network model using the original datasets and labels provide further improvements, attaining the state-of-the-art results on the KITTI-2015 scene flow benchmark in the non-stereo category. Our method achieves the best foreground accuracy (4.33% in Fl-all) over both the stereo and non-stereo categories, even though using only monocular image inputs.Keywords
All Related Versions
Funding Information
- National Research Foundation of Korea (2021R1A2C3006659)
This publication has 27 references indexed in Scilit:
- FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks2017
- Optical Flow Estimation Using a Spatial Pyramid Network2017
- The HCI Benchmark Suite: Stereo and Flow Ground Truth with Uncertainties for Urban Autonomous Driving2016
- A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation2016
- FlowNet: Learning Optical Flow with Convolutional Networks2015
- Moving object tracking using optical flow and motion vector estimation2015
- Object scene flow for autonomous vehicles2015
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Determining Optical Flow1981