CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow
Authors:
Top Cited Papers
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 17581-17590
Abstract
Optical flow estimation aims to find the 2D motion field by identifying corresponding pixels between two images. Despite the tremendous progress of deep learning-based optical flow methods, it remains a challenge to accurately estimate large displacements with motion blur. This is mainly because the correlation volume, the basis of pixel matching, is computed as the dot product of the convolutional features of the two images. The locality of convolutional features makes the computed correlations susceptible to various noises. On large displacements with motion blur, noisy correlations could cause severe errors in the estimated flow. To overcome this challenge, we propose a new architecture “CRoss-Attentional Flow Trans-former” (CRAFT), aiming to revitalize the correlation volume computation. In CRAFT, a Semantic Smoothing Trans-former layer transforms the features of one frame, making them more global and semantically stable. In addition, the dot-product correlations are replaced with trans-former Cross-Frame Attention. This layer filters out feature noises through the Query and Key projections, and computes more accurate correlations. On Sintel (Final) and KITTI (foreground) benchmarks, CRAFT has achieved new state-of-the-art performance. Moreover, to test the robust-ness of different models on large motions, we designed an image shifting attack that shifts input images to generate large artificial motions. Under this attack, CRAFT per-forms much more robustly than two representative meth-ods, RAFT and GMA. The code of CRAFT is is available at https://github.com/askerlee/craft.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition2018
- Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation2018
- FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks2017
- Slow Flow: Exploiting High-Speed Cameras for Accurate and Diverse Optical Flow Reference Data2017
- Optical Flow Estimation Using a Spatial Pyramid Network2017
- Accurate Optical Flow via Direct Cost Volume Processing2017
- 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
- JOINT 3D ESTIMATION OF VEHICLES AND SCENE FLOWISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2015