Devon: Deformable Volume Network for Learning Optical Flow

02/20/2018
by   Yao Lu, et al.
0

We propose a lightweight neural network model, Deformable Volume Network (Devon) for learning optical flow. Devon benefits from a multi-stage framework to iteratively refine its prediction. Each stage is by itself a neural network with an identical architecture. The optical flow between two stages is propagated with a newly proposed module, the deformable cost volume. The deformable cost volume does not distort the original images or their feature maps and therefore avoids the artifacts associated with warping, a common drawback in previous models. Devon only has one million parameters. Experiments show that Devon achieves comparable results to previous neural network models, despite of its small size.

READ FULL TEXT

page 2

page 7

page 8

research
09/07/2017

PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume

We present a compact but effective CNN model for optical flow, called PW...
research
04/17/2023

LLA-FLOW: A Lightweight Local Aggregation on Cost Volume for Optical Flow Estimation

Lack of texture often causes ambiguity in matching, and handling this is...
research
01/31/2021

OAS-Net: Occlusion Aware Sampling Network for Accurate Optical Flow

Optical flow estimation is an essential step for many real-world compute...
research
03/31/2021

DCVNet: Dilated Cost Volume Networks for Fast Optical Flow

The cost volume, capturing the similarity of possible correspondences ac...
research
06/09/2023

DIFT: Dynamic Iterative Field Transforms for Memory Efficient Optical Flow

Recent advancements in neural network-based optical flow estimation ofte...
research
06/08/2023

FlowFormer: A Transformer Architecture and Its Masked Cost Volume Autoencoding for Optical Flow

This paper introduces a novel transformer-based network architecture, Fl...
research
07/18/2020

LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation

Deep learning approaches have achieved great success in addressing the p...

Please sign up or login with your details

Forgot password? Click here to reset