AI Paper Atlas

Research map / Detection and segmentation / CNN features

SegStereo: Exploiting Semantic Information for Disparity Estimation

Guorun Yang, Hengshuang Zhao, Jianping Shi, Zhidong Deng, Jiaya Jia

ECCV 2018 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 401 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add semantic feature embedding (PSPNet features) to ResNetCorr (ablation)photometric-loss stereo net · KITTI Stereo 2015 (unsupervised, all pixels)EPE: 3.36 -> 2.72Improved
add semantic feature embedding (ablation)photometric-loss stereo net · KITTI Stereo 2015 (unsupervised, all pixels)D1 error: 14.08 -> 12.08Improved
add semantic feature embedding (ablation)photometric + smooth loss net · KITTI Stereo 2015 (unsupervised, all pixels)EPE: 2.43 -> 2.17Improved
add smoothness loss (ablation)SegStereo (photometric) · KITTI Stereo 2015 (unsupervised, all pixels)EPE: 2.72 -> 2.17Improved
add semantic softmax loss (ablation)SegStereo (photometric + smooth) · KITTI Stereo 2015 (unsupervised, all pixels)EPE: 2.17 -> 1.89Improved
add semantic softmax loss (ablation)SegStereo (photometric + smooth) · KITTI Stereo 2015 (unsupervised, all pixels)D1 error: 10.53 -> 10.03Improved
fine-tune on 200 KITTI 2015 training imagesSegStereo unsupervised · KITTI Stereo 2015 (unsupervised, all pixels)D1 error: 10.03 -> 8.79Improved
add semantic feature embedding (pretrain on Cityscapes) (ablation)supervised stereo net · KITTI 2015 test splitD1 error (All): 7.64 -> 7.34Improved
add semantic feature embedding (pretrain on extra Cityscapes + FlyingThings3D) (ablation)supervised stereo net · KITTI 2015 test splitD1 error (All): 5.64 -> 5.38Improved
add semantic feature embedding after finetuning (ablation)supervised stereo net · KITTI 2012+2015 finetuned, validation splitEPE (All): 0.76 -> 0.75No clear effect
use finer shallow layer conv1_3 with correlation 96 (corr13)SegStereo · KITTI 2012+2015 finetuned, validation splitD1 error (All): 2.30 -> 2.25Improved
add semantic cues to ResNetCorr (ablation)supervised stereo net · FlyingThings3D testEPE: 3.50 -> 1.45Improved

Later papers that compared with this method

1 later accepted paper reports SegStereo as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy