Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Sampling the disparity space image.

Richard Szeliski1, Daniel Scharstein

  • 1Microsoft Research, One Microsoft Way, Redmond, WA 98052, USA. szeliski@microsoft.com

IEEE Transactions on Pattern Analysis and Machine Intelligence
|September 21, 2004
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Guest Editorial: Special Section on CVPR 2013.

IEEE transactions on pattern analysis and machine intelligence·2016
Same author

Modeling Radiometric Uncertainty for Vision with Tone-Mapped Color Images.

IEEE transactions on pattern analysis and machine intelligence·2015
Same author

Pushing the envelope of modern methods for bundle adjustment.

IEEE transactions on pattern analysis and machine intelligence·2012
Same author

Image restoration by matching gradient distributions.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

PMF and its influence on computational stereo.

Perception·2009
Same author

Evaluation of stereo matching costs on images with radiometric differences.

IEEE transactions on pattern analysis and machine intelligence·2009
Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Achieving Text-based Person Retrieval with Any Granularity.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study improves stereo vision algorithms by introducing new matching cost functions. Analyzing the continuous disparity space image (DSI) and using interpolated signals enhances stereo matching accuracy.

Area of Science:

  • Computer Vision
  • Image Processing
  • Stereo Vision

Background:

  • A key challenge in stereo algorithm design is selecting an appropriate matching cost.
  • Current methods often rely on simple intensity differences with integer disparity steps, which can be suboptimal.

Purpose of the Study:

  • To investigate the limitations of traditional matching costs in stereo vision.
  • To propose and evaluate novel matching cost functions for improved stereo matching performance.

Main Methods:

  • Analysis of the continuous disparity space image (DSI) properties.
  • Development of new matching cost variants using symmetrically matched, interpolated image signals.
  • Empirical evaluation using stereo images with ground truth data.

Related Experiment Videos

Main Results:

  • Demonstrated that novel matching cost variants outperform traditional methods.
  • Showcased the benefits of proper sampling in the continuous disparity space.
  • Quantified improvements in stereo matching accuracy.

Conclusions:

  • The proposed matching cost variants offer a significant advancement in stereo algorithm design.
  • Interpolated image signals and careful sampling are crucial for accurate stereo matching.
  • This research provides a foundation for more robust and precise stereo vision systems.