DDFlow: Learning Optical Flow with Unlabeled Data Distillation

02/25/2019
by   Pengpeng Liu, et al.
8

We present DDFlow, a data distillation approach to learning optical flow estimation from unlabeled data. The approach distills reliable predictions from a teacher network, and uses these predictions as annotations to guide a student network to learn optical flow. Unlike existing work relying on hand-crafted energy terms to handle occlusion, our approach is data-driven, and learns optical flow for occluded pixels. This enables us to train our model with a much simpler loss function, and achieve a much higher accuracy. We conduct a rigorous evaluation on the challenging Flying Chairs, MPI Sintel, KITTI 2012 and 2015 benchmarks, and show that our approach significantly outperforms all existing unsupervised learning methods, while running at real time.

READ FULL TEXT

page 2

page 3

page 4

page 6

research
06/08/2021

Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation

We present DistillFlow, a knowledge distillation approach to learning op...
research
11/16/2017

Occlusion Aware Unsupervised Learning of Optical Flow

It has been recently shown that a convolutional neural network can learn...
research
09/30/2021

Sensor-Guided Optical Flow

This paper proposes a framework to guide an optical flow network with ex...
research
12/01/2020

UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning

We present an unsupervised learning approach for optical flow estimation...
research
08/14/2023

The Devil in the Details: Simple and Effective Optical Flow Synthetic Data Generation

Recent work on dense optical flow has shown significant progress, primar...
research
11/04/2020

CoT-AMFlow: Adaptive Modulation Network with Co-Teaching Strategy for Unsupervised Optical Flow Estimation

The interpretation of ego motion and scene change is a fundamental task ...
research
06/08/2020

What Matters in Unsupervised Optical Flow

We systematically compare and analyze a set of key components in unsuper...

Please sign up or login with your details

Forgot password? Click here to reset