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

Spacetime stereo: a unifying framework for depth from triangulation.

James Davis1, Diego Nehab, Ravi Ramamoorthi

  • 1Honda Research Institute, Mountain View, CA 94041, USA. jedavis@ieee.org

IEEE Transactions on Pattern Analysis and Machine Intelligence
|February 4, 2005
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

Cardiovascular Risk Factors - Lifestyle Modifications.

The New England journal of medicine·2026
Same author

Cost Analysis of an Outpatient MRI Pathway for Optic Disc Edema: A Time-Driven Activity-Based Costing Approach.

American journal of ophthalmology·2026
Same author

Plasma carotenoids and (poly)phenols in people living with an ileostomy: associations with dietary intake.

Food & function·2026
Same author

Tobacco-specific alkaloid (TSA) formation in aged e-cigarette juices: mechanistic insights into hydroxyl radical-initiated nicotine oxidation.

Environmental science. Processes & impacts·2026
Same author

Discrepancy in Estimating GFR for Melphalan Dosing in Multiple Myeloma Patients Undergoing Autologous Stem Cell Transplant: A Retrospective Analysis.

Kidney360·2026
Same author

Exophthalmos and Buphthalmos in Broiler Breeders Associated with Marek's Disease Virus.

Avian diseases·2026
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 introduces spacetime stereo, a unified framework for depth estimation. It enables new algorithms that improve depth recovery in challenging scenarios where traditional methods fail.

Area of Science:

  • Computer Vision
  • 3D Reconstruction
  • Robotics

Background:

  • Depth estimation methods like stereo, laser scanning, and structured light are typically studied independently.
  • Existing techniques have limitations in certain environments and dynamic scenes.

Purpose of the Study:

  • To propose a unified framework, spacetime stereo, for depth estimation.
  • To develop novel algorithms for depth recovery using this framework.
  • To demonstrate improved performance in challenging depth estimation scenarios.

Main Methods:

  • Developed the spacetime stereo framework, unifying diverse depth estimation approaches.
  • Created new algorithms for depth from unstructured illumination change.
  • Enabled depth estimation in dynamic scenes using the unified framework.

Related Experiment Videos

Main Results:

  • The spacetime stereo framework successfully integrates various depth estimation techniques.
  • Novel algorithms demonstrate effective depth recovery from illumination changes.
  • The framework shows superior performance in dynamic scenes compared to traditional methods.

Conclusions:

  • Spacetime stereo provides a generalized approach to depth from triangulation.
  • New algorithms offer robust depth estimation in previously difficult situations.
  • This unified framework advances the field of 3D computer vision.