Search research articles

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

Targetless Calibration of Wide-Baseline and Wide-Angle Surround-View Fisheye Cameras Using Cylindrical Projection Model.

Sensors (Basel, Switzerland)·2026

Same author

Eigenpose: Occlusion-Robust 3D Human Mesh Reconstruction.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025

Same author

6DoF Object Pose and Focal Length Estimation from Single RGB Images in Uncontrolled Environments.

Sensors (Basel, Switzerland)·2024

Same author

Extrinsic Calibration between Camera and LiDAR Sensors by Matching Multiple 3D Planes.

Sensors (Basel, Switzerland)·2019

Same author

Deep vector-based convolutional neural network approach for automatic recognition of colonies of induced pluripotent stem cells.

PloS one·2017

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: Oct 17, 2025

A Postoperative Evaluation Guideline for Computer-Assisted Reconstruction of the Mandible

A Postoperative Evaluation Guideline for Computer-Assisted Reconstruction of the Mandible

Published on: January 28, 2020

Enhanced Soft 3D Reconstruction Method with an Iterative Matching Cost Update Using Object Surface Consensus.

Min-Jae Lee¹, Gi-Mun Um², Joungil Yun²

¹Graduate School of Electronics and Electrical Engineering, Kyungpook National University, Daegu 41566, Korea.

Sensors (Basel, Switzerland)

|October 13, 2021

Summary

This summary is machine-generated.

EnSoft3D enhances multi-view stereo matching for high-quality 3D depth images. This method iteratively updates matching costs, improving accuracy and view synthesis over prior techniques.

Keywords:

iterative multi-view stereo matching refinement stereo vision view synthesis

More Related Videos

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

Correlative Microscopy for 3D Structural Analysis of Dynamic Interactions

Correlative Microscopy for 3D Structural Analysis of Dynamic Interactions

Published on: June 24, 2013

Related Experiment Videos

Last Updated: Oct 17, 2025

A Postoperative Evaluation Guideline for Computer-Assisted Reconstruction of the Mandible

A Postoperative Evaluation Guideline for Computer-Assisted Reconstruction of the Mandible

Published on: January 28, 2020

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

Correlative Microscopy for 3D Structural Analysis of Dynamic Interactions

Correlative Microscopy for 3D Structural Analysis of Dynamic Interactions

Published on: June 24, 2013

Area of Science:

Computer Vision
3D Reconstruction

Background:

Multi-view stereo (MVS) is crucial for 3D reconstruction and novel view synthesis.
Existing methods like Soft3D reconstruct depth but suffer from un-updated Plane Sweep Stereo (PSS) matching costs, limiting accuracy.

Purpose of the Study:

To introduce EnSoft3D (Enhanced Soft 3D Reconstruction), a novel MVS method.
To improve the accuracy and quality of dense depth image reconstruction.
To enhance novel view synthesis capabilities by addressing limitations in prior methods.

Main Methods:

EnSoft3D iteratively updates PSS matching costs using an inverse consensus kernel derived from an object surface consensus volume.
It simultaneously refines multi-view matching costs and soft visibility volumes.
The method integrates PSS matching costs with soft visibility for occlusion-aware depth reconstruction.

Main Results:

EnSoft3D reconstructs highly accurate 3D depth images.
Evaluations on benchmark datasets show reduced disparity error, verifying improved 3D reconstruction accuracy.
Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) indicate simultaneous enhancement of view synthesis.

Conclusions:

The proposed EnSoft3D method effectively overcomes limitations of previous Soft3D approaches.
Simultaneous updates of matching costs and visibility volumes lead to superior depth reconstruction and view synthesis.
EnSoft3D offers a robust solution for generating dense, high-quality depth maps in multi-view stereo applications.