Expansion of Visual Hints for Improved Generalization in Stereo Matching

Andrea Pilzer*, Yuxin Hou, Niki Loppi, Arno Solin, Juho Kannala

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

1 Citation (Scopus)


We introduce visual hints expansion for guiding stereo matching to improve generalization. Our work is motivated by the robustness of Visual Inertial Odometry (VIO) in computer vision and robotics, where a sparse and unevenly distributed set of feature points characterizes a scene. To improve stereo matching, we propose to elevate 2D hints to 3D points. These sparse and unevenly distributed 3D visual hints are expanded using a 3D random geometric graph, which enhances the learning and inference process. We evaluate our proposal on multiple widely adopted benchmarks and show improved performance without access to additional sensors other than the image sequence. To highlight practical applicability and symbiosis with visual odometry, we demonstrate how our methods run on embedded hardware.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023
Number of pages10
ISBN (Electronic)978-1-6654-9346-8
Publication statusPublished - 2023
MoE publication typeA4 Article in a conference publication
EventIEEE Winter Conference on Applications of Computer Vision - Waikoloa, United States
Duration: 2 Jan 20237 Jan 2023


ConferenceIEEE Winter Conference on Applications of Computer Vision
Abbreviated titleWACV
Country/TerritoryUnited States


  • Algorithms: 3D computer vision


Dive into the research topics of 'Expansion of Visual Hints for Improved Generalization in Stereo Matching'. Together they form a unique fingerprint.

Cite this