Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 14, 2026

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment

Published on: January 6, 2026

DAISY: an efficient dense descriptor applied to wide-baseline stereo.

Engin Tola¹, Vincent Lepetit, Pascal Fua

¹Ecole Polytechnic Fédérale de Lausanne (EPFL), Lausanne, Switzerland. engin.tola@epfl.ch

IEEE Transactions on Pattern Analysis and Machine Intelligence

|March 20, 2010

Summary

This study introduces DAISY, an efficient local image descriptor, for computing dense depth and occlusion maps from wide-baseline stereo images. The novel approach demonstrates superior accuracy and robustness against transformations, outperforming existing methods.

Related Concept Videos

Depth Perception and Spatial Vision

Depth Perception and Spatial Vision

Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.

You might also read

Related Articles

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

Sort by

Same author

Two Projections Suffice for Cerebral Vascular Reconstruction.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2025

Same author

Temporally-Consistent Surface Reconstruction Using Metrically-Consistent Atlases.

IEEE transactions on pattern analysis and machine intelligence·2025

Same author

Harnessing deep learning to detect bronchiolitis obliterans syndrome from chest CT.

Communications medicine·2025

Same author

<i>MedShapeNet</i> - a large-scale dataset of 3D medical shapes for computer vision.

Biomedizinische Technik. Biomedical engineering·2024

Same author

Efficient anatomical labeling of pulmonary tree structures via deep point-graph representation-based implicit fields.

Medical image analysis·2024

Same author

Author Correction: BigNeuron: a resource to benchmark and predict performance of algorithms for automated tracing of neurons in light microscopy datasets.

Nature methods·2024

Area of Science:

Computer Vision
Image Processing
Robotics

Background:

Wide-baseline stereo vision presents challenges for dense depth estimation.
Existing methods struggle with photometric and geometric variations.
Efficient and robust local image descriptors are crucial for stereo matching.

Purpose of the Study:

Introduce DAISY, a novel, computationally efficient local image descriptor.
Develop an EM-based algorithm for dense depth and occlusion map computation using DAISY.
Evaluate the performance of the proposed method in wide-baseline stereo scenarios.

Main Methods:

DAISY descriptor computation for dense image analysis.
Expectation-Maximization (EM) algorithm for depth and occlusion estimation.

Related Experiment Videos

Last Updated: Jun 14, 2026

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment

Published on: January 6, 2026

Comparative analysis against pixel/correlation-based methods and other descriptors (SIFT, GLOH, SURF).

Main Results:

Achieved significantly better results in wide-baseline stereo compared to traditional methods.
Demonstrated robustness against various photometric and geometric transformations.
Validated accuracy through experiments on laser-scanned ground truth scenes and diverse indoor/outdoor environments.

Conclusions:

DAISY enables the first successful dense depth map estimation from wide-baseline image pairs.
The proposed EM-based algorithm offers a robust and accurate solution for challenging stereo vision tasks.
DAISY descriptor provides a faster and artifact-free alternative for dense matching applications.