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 Video

Updated: Jun 24, 2026

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

Make3D: learning 3D scene structure from a single still image.

Ashutosh Saxena1, Min Sun, Andrew Y Ng

  • 1Computer Science Department,Stanford University, Gates Building 1A, Computer Science, 353 SerraMall, Stanford, CA 94305-9010. {asaxena, ang}@cs.stanford.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|March 21, 2009
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

STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology.

Advances in neural information processing systems·2026
Same author

STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology.

ArXiv·2026
Same author

Right Patient, Right Specialist, Right Time: Retrieval Augmented Generation for Specialty Referral Routing.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same author

Regional mapping of natural gas compressor stations in the United States and Canada using deep learning on satellite imagery.

Journal of environmental management·2025
Same author

Deep learning for detecting and characterizing oil and gas well pads in satellite imagery.

Nature communications·2024
Same author

Probabilistic Prediction of Laboratory Test Information Yield.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2024
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

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

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

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

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

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

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

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

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

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

Learning Shape Anchors for Holistic Indoor Scene Understanding.

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

This study introduces a novel method for generating detailed 3D models from single images using Markov Random Fields (MRFs). The approach accurately reconstructs complex scenes, enhancing 3D visualization and flythrough experiences.

Area of Science:

  • Computer Vision
  • 3D Reconstruction
  • Machine Learning

Background:

  • Estimating detailed 3D structure from single images is challenging.
  • Existing methods often lack quantitative accuracy and visual appeal.
  • Unstructured environments pose difficulties for traditional 3D modeling.

Purpose of the Study:

  • To develop a method for creating accurate and visually pleasing 3D models from single still images.
  • To infer detailed 3D structure, including location and orientation, of image patches.
  • To enable richer 3D flythrough experiences using image-based rendering.

Main Methods:

  • Utilizing a Markov Random Field (MRF) to infer plane parameters for image patches.
  • Training the MRF with supervised learning, incorporating image depth cues and inter-patch relationships.

More Related Videos

Single-Cell Resolution Three-Dimensional Imaging of Intact Organoids
10:40

Single-Cell Resolution Three-Dimensional Imaging of Intact Organoids

Published on: June 5, 2020

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques
11:34

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

Published on: December 3, 2013

Related Experiment Videos

Last Updated: Jun 24, 2026

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

Single-Cell Resolution Three-Dimensional Imaging of Intact Organoids
10:40

Single-Cell Resolution Three-Dimensional Imaging of Intact Organoids

Published on: June 5, 2020

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques
11:34

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

Published on: December 3, 2013

  • Making minimal assumptions about scene structure, allowing for detailed reconstruction.

    • Main Results:

    • Achieved qualitatively correct 3D models for 64.9% of 588 internet images.
    • Demonstrated the ability to capture detailed 3D structure beyond prior art.
    • Extended the model for large-scale 3D modeling from multiple images.

    Conclusions:

    • The MRF-based approach effectively estimates detailed 3D structure from single images.
    • The method surpasses prior art in detail and visual richness for 3D flythroughs.
    • The model shows promise for both single-image and multi-image 3D reconstruction tasks.