RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

03/26/2020
by   Zachary Teed, et al.
3

We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network architecture for optical flow. RAFT extracts per-pixel features, builds multi-scale 4D correlation volumes for all pairs of pixels, and iteratively updates a flow field through a recurrent unit that performs lookups on the correlation volumes. RAFT achieves state-of-the-art performance, with strong cross-dataset generalization and high efficiency in inference time, training speed, and parameter count. Code is available <https://github.com/princeton-vl/RAFT>.

READ FULL TEXT

page 9

page 10

page 14

research
09/14/2020

PRAFlow_RVC: Pyramid Recurrent All-Pairs Field Transforms for Optical Flow Estimation in Robust Vision Challenge 2020

Optical flow estimation is an important computer vision task, which aims...
research
04/19/2023

AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation

We present All-Pairs Multi-Field Transforms (AMT), a new network archite...
research
05/09/2022

Multiview Stereo with Cascaded Epipolar RAFT

We address multiview stereo (MVS), an important 3D vision task that reco...
research
04/05/2021

Learning Optical Flow from a Few Matches

State-of-the-art neural network models for optical flow estimation requi...
research
09/22/2022

Poisson Flow Generative Models

We propose a new "Poisson flow" generative model (PFGM) that maps a unif...
research
03/31/2022

CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow

Optical flow estimation aims to find the 2D motion field by identifying ...
research
11/21/2022

FlowLens: Seeing Beyond the FoV via Flow-guided Clip-Recurrent Transformer

Limited by hardware cost and system size, camera's Field-of-View (FoV) i...

Please sign up or login with your details

Forgot password? Click here to reset