MLP-Stereo: Heterogeneous Feature Fusion in MLP for Stereo Matching

CNNs' strong inductive biases of locality and weight sharing provide powerful representation ability and data sample utilization efficiency. However, the weight sharing might smooth out the discrepancy between similar pixels, resulting in the wrong matching between left and right camera-image p...

Full description

Saved in:
Bibliographic Details
Main Authors: Ye, Shuiqiang, Zeng, Pengcheng, Li, Pengfei, Wang, Weiqi, Xinan, Wang, Zhao, Yong
Format: Conference Proceeding
Language:English
Subjects:
Convolution
cost aggregation
Costs
Image processing
inductive bias
MLP
real-time network
Real-time systems
Stereo matching
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:CNNs' strong inductive biases of locality and weight sharing provide powerful representation ability and data sample utilization efficiency. However, the weight sharing might smooth out the discrepancy between similar pixels, resulting in the wrong matching between left and right camera-image pair in thin structures region and repetitive texture region. In this paper, we propose a novel Heterogeneous Feature Fusion in MLP (HFF-MLP) for Stereo matching. It employs MLP structure and relaxes the weights sharing in the local spatial region. To this end, pixels in thin structures region and repetitive texture region are dealt with independently using the exclusive weights. Based on HFF -MLP module, we design a real-time network, i.e., MLP-Stereo. Experimental results show that our proposed HFF-MLP achieves competitive results on KITTI 2015 test dataset with the running time of 46 milliseconds. Furthermore, it performs much better than other real-time network in thin structures region and repetitive texture region.
ISSN:2381-8549
DOI:10.1109/ICIP46576.2022.9897348