Stereo Superpixel Segmentation Via Decoupled Dynamic Spatial-Embedding Fusion Network

TL;DR

This paper introduces a novel stereo superpixel segmentation method that decouples and adaptively fuses spatial and disparity information, achieving state-of-the-art results on multiple datasets.

Contribution

It proposes a decoupling mechanism and dynamic fusion modules to improve stereo superpixel segmentation by better handling spatial and disparity features.

Findings

Achieves state-of-the-art performance on KITTI2015 and Cityscapes datasets.

Demonstrates efficiency in salient object detection on NJU2K dataset.

Outperforms existing algorithms in segmentation quality.

Abstract

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.