AI Paper Atlas

Research map / Detection and segmentation / CNN features

Semantic Stereo Matching With Pyramid Cost Volumes

Zhenyao Wu, Xinyi Wu, Xiaoping Zhang, Song Wang, Lili Ju

ICCV 2019 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 140 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 branch to single spatial cost volume (ablation)single-cost-volume stereo net · Scene Flow validationend-point error: 2.12 -> 1.76Improved
add semantic branch to single spatial cost volume (ablation)single-cost-volume stereo net · KITTI 2015 validationerror rate (%): 2.63 -> 2.42Improved
add joint training of semantic branch (ablation)semantic branch variant · Scene Flow validationend-point error: 1.76 -> 1.78No clear effect
add joint training of semantic branch (ablation)semantic branch variant · KITTI 2015 validationerror rate (%): 2.42 -> 2.37Improved
use spatial pyramid cost volumes (ablation)single-cost-volume stereo net · Scene Flow validationend-point error: 2.12 -> 1.21Improved
use spatial pyramid cost volumes (ablation)single-cost-volume stereo net · KITTI 2015 validationerror rate (%): 2.63 -> 2.11Improved
add 3D multiple cost volumes (ablation)pyramid cost volume variant · Scene Flow validationend-point error: 1.21 -> 1.04Improved
add 3D multiple cost volumes (ablation)pyramid cost volume variant · KITTI 2015 validationerror rate (%): 2.11 -> 1.99Improved
add 3D feature fusion module (FFM) (ablation)SSPCV-Net · Scene Flow validationend-point error: 1.07 -> 0.98Improved
add 3D feature fusion module (FFM) (ablation)SSPCV-Net · KITTI 2015 validationerror rate (%): 2.10 -> 1.85Improved
add boundary loss in joint training (ablation)SSPCV-Net · Scene Flow validationend-point error: 1.01 -> 0.98Improved
add boundary loss in joint training (ablation)SSPCV-Net · KITTI 2015 validationerror rate (%): 1.93 -> 1.85Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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