Displacement-Invariant Cost Computation for Efficient Stereo Matching

12/01/2020
by   Yiran Zhong, et al.
9

Although deep learning-based methods have dominated stereo matching leaderboards by yielding unprecedented disparity accuracy, their inference time is typically slow, on the order of seconds for a pair of 540p images. The main reason is that the leading methods employ time-consuming 3D convolutions applied to a 4D feature volume. A common way to speed up the computation is to downsample the feature volume, but this loses high-frequency details. To overcome these challenges, we propose a displacement-invariant cost computation module to compute the matching costs without needing a 4D feature volume. Rather, costs are computed by applying the same 2D convolution network on each disparity-shifted feature map pair independently. Unlike previous 2D convolution-based methods that simply perform context mapping between inputs and disparity maps, our proposed approach learns to match features between the two images. We also propose an entropy-based refinement strategy to refine the computed disparity map, which further improves speed by avoiding the need to compute a second disparity map on the right image. Extensive experiments on standard datasets (SceneFlow, KITTI, ETH3D, and Middlebury) demonstrate that our method achieves competitive accuracy with much less inference time. On typical image sizes, our method processes over 100 FPS on a desktop GPU, making our method suitable for time-critical applications such as autonomous driving. We also show that our approach generalizes well to unseen datasets, outperforming 4D-volumetric methods.

READ FULL TEXT

page 3

page 5

page 6

page 7

page 8

research
03/08/2019

Fast Deep Stereo with 2D Convolutional Processing of Cost Signatures

Modern neural network-based algorithms are able to produce highly accura...
research
08/12/2021

Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation

Volumetric deep learning approach towards stereo matching aggregates a c...
research
02/05/2023

A Disparity Refinement Framework for Learning-based Stereo Matching Methods in Cross-domain Setting for Laparoscopic Images

Purpose: Stereo matching methods that enable depth estimation are crucia...
research
08/27/2018

Stereo Computation for a Single Mixture Image

This paper proposes an original problem of stereo computation from a sin...
research
04/05/2018

CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation

Recently, there has been a paradigm shift in stereo matching with learni...
research
05/17/2019

CNN-based Cost Volume Analysis as Confidence Measure for Dense Matching

Due to its capability to identify erroneous disparity assignments in den...
research
10/26/2020

EDNet: Improved DispNet for Efficient Disparity Estimation

Given a pair of rectified images, the goal of stereo matching is to esti...

Please sign up or login with your details

Forgot password? Click here to reset