Stereo Superpixel Segmentation Via Decoupled Dynamic Spatial-Embedding Fusion Network

08/17/2022
by   Hua Li, et al.
0

Stereo superpixel segmentation aims at grouping the discretizing pixels into perceptual regions through left and right views more collaboratively and efficiently. Existing superpixel segmentation algorithms mostly utilize color and spatial features as input, which may impose strong constraints on spatial information while utilizing the disparity information in terms of stereo image pairs. To alleviate this issue, we propose a stereo superpixel segmentation method with a decoupling mechanism of spatial information in this work. To decouple stereo disparity information and spatial information, the spatial information is temporarily removed before fusing the features of stereo image pairs, and a decoupled stereo fusion module (DSFM) is proposed to handle the stereo features alignment as well as occlusion problems. Moreover, since the spatial information is vital to superpixel segmentation, we further design a dynamic spatiality embedding module (DSEM) to re-add spatial information, and the weights of spatial information will be adaptively adjusted through the dynamic fusion (DF) mechanism in DSEM for achieving a finer segmentation. Comprehensive experimental results demonstrate that our method can achieve the state-of-the-art performance on the KITTI2015 and Cityscapes datasets, and also verify the efficiency when applied in salient object detection on NJU2K dataset. The source code will be available publicly after paper is accepted.

READ FULL TEXT

page 1

page 2

page 4

page 5

page 7

page 8

page 9

research
04/18/2023

Saliency-aware Stereoscopic Video Retargeting

Stereo video retargeting aims to resize an image to a desired aspect rat...
research
09/16/2020

Parallax Attention for Unsupervised Stereo Correspondence Learning

Stereo image pairs encode 3D scene cues into stereo correspondences betw...
research
11/18/2022

Stereo Image Rain Removal via Dual-View Mutual Attention

Stereo images, containing left and right view images with disparity, are...
research
06/09/2020

Stereo RGB and Deeper LIDAR Based Network for 3D Object Detection

3D object detection has become an emerging task in autonomous driving sc...
research
03/18/2018

Sdf-GAN: Semi-supervised Depth Fusion with Multi-scale Adversarial Networks

Fusing disparity maps from different algorithms to exploit their complem...
research
10/27/2020

Stereo Frustums: A Siamese Pipeline for 3D Object Detection

The paper proposes a light-weighted stereo frustums matching module for ...
research
06/14/2020

Geometry-Aware Instance Segmentation with Disparity Maps

Most previous works of outdoor instance segmentation for images only use...

Please sign up or login with your details

Forgot password? Click here to reset