Learning Optical Flow via Dilated Networks and Occlusion Reasoning

05/07/2018
by   Yi Zhu, et al.
0

Despite the significant progress that has been made on estimating optical flow recently, most estimation methods, including classical and deep learning approaches, still have difficulty with multi-scale estimation, real-time computation, and/or occlusion reasoning. In this paper, we introduce dilated convolution and occlusion reasoning into unsupervised optical flow estimation to address these issues. The dilated convolution allows our network to avoid upsampling via deconvolution and the resulting gridding artifacts. Dilated convolution also results in a smaller memory footprint which speeds up interference. The occlusion reasoning prevents our network from learning incorrect deformations due to occluded image regions during training. Our proposed method outperforms state-of-the-art unsupervised approaches on the KITTI benchmark. We also demonstrate its generalization capability by applying it to action recognition in video.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/30/2020

OccInpFlow: Occlusion-Inpainting Optical Flow Estimation by Unsupervised Learning

Occlusion is an inevitable and critical problem in unsupervised optical ...
research
11/16/2017

Occlusion Aware Unsupervised Learning of Optical Flow

It has been recently shown that a convolutional neural network can learn...
research
04/10/2019

Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation

Deep learning approaches to optical flow estimation have seen rapid prog...
research
04/11/2018

Multi-Scale Generalized Plane Match for Optical Flow

Despite recent advances, estimating optical flow remains a challenging p...
research
11/26/2019

DDNet: Dual-path Decoder Network for Occlusion Relationship Reasoning

Occlusion relationship reasoning based on convolution neural networks co...
research
07/25/2022

Multi-Scale RAFT: Combining Hierarchical Concepts for Learning-based Optical FLow Estimation

Many classical and learning-based optical flow methods rely on hierarchi...
research
09/20/2023

Conformalized Multimodal Uncertainty Regression and Reasoning

This paper introduces a lightweight uncertainty estimator capable of pre...

Please sign up or login with your details

Forgot password? Click here to reset