SegStereo: Exploiting Semantic Information for Disparity Estimation

2018-07-31 · ECCV 2018 9 · Guorun Yang, Hengshuang Zhao, Jianping Shi, Zhidong Deng, Jiaya Jia

Disparity estimation for binocular stereo images finds a wide range of applications. Traditional algorithms may fail on featureless regions, which could be handled by high-level clues such as semantic segments. In this paper, we suggest that appropriate incorporation of semantic cues can greatly rectify prediction in commonly-used disparity estimation frameworks. Our method conducts semantic feature embedding and regularizes semantic cues as the loss term to improve learning disparity. Our unified model SegStereo employs semantic features from segmentation and introduces semantic softmax loss, which helps improve the prediction accuracy of disparity maps. The semantic cues work well in both unsupervised and supervised manners. SegStereo achieves state-of-the-art results on KITTI Stereo benchmark and produces decent prediction on both CityScapes and FlyingThings3D datasets.

📄 PDF Abstract BibTeX arXiv:1807.11699

Code (0)

등록된 구현이 없습니다.

Tasks

Disparity Estimation Prediction Semantic Segmentation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

USAM-Net: A U-Net-based Network for Improved Stereo Correspondence and Scene Depth Estimation using Features from a Pre-trained Image Segmentation network

2025-03-19 · Joseph Emmanuel DL Dayo, Prospero C. Naval Jr

The increasing demand for high-accuracy depth estimation in autonomous driving and augmented reality applications necessitates advanced neural architectures capable of effectively leveraging multiple data modalities. In …

Autonomous Driving Depth Estimation Image Segmentation Segmentation+2

S3Net: Innovating Stereo Matching and Semantic Segmentation with a Single-Branch Semantic Stereo Network in Satellite Epipolar Imagery

2024-01-03 · Qingyuan Yang, Guanzhou Chen, Xiaoliang Tan, Tong Wang 외

Stereo matching and semantic segmentation are significant tasks in binocular satellite 3D reconstruction. However, previous studies primarily view these as independent parallel tasks, lacking an integrated multitask lear…

3D Reconstruction Disparity Estimation Segmentation Semantic Segmentation+1

DispSegNet: Leveraging Semantics for End-to-End Learning of Disparity Estimation from Stereo Imagery

2018-09-13 · Jun-ming Zhang, Katherine A. Skinner, Ram Vasudevan, Matthew Johnson-Roberson

Recent work has shown that convolutional neural networks (CNNs) can be applied successfully in disparity estimation, but these methods still suffer from errors in regions of low-texture, occlusions and reflections. Concu…

Disparity Estimation Segmentation Semantic Segmentation

Self-Supervised Light Field Depth Estimation Using Epipolar Plane Images

2022-03-29 · Kunyuan Li, Jun Zhang, Jun Gao, Meibin Qi

Exploiting light field data makes it possible to obtain dense and accurate depth map. However, synthetic scenes with limited disparity range cannot contain the diversity of real scenes. By training in synthetic data, cur…

Depth Estimation Diversity Self-Supervised Learning

Fast Disparity Estimation using Dense Networks

2018-05-19 · Rowel Atienza

Disparity estimation is a difficult problem in stereo vision because the correspondence technique fails in images with textureless and repetitive regions. Recent body of work using deep convolutional neural networks (CNN…

Disparity Estimation