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

Related Concept Videos

Residuals and Least-Squares Property

Residuals and Least-Squares Property

The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...

You might also read

Related Articles

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

Sort by

Same author

Type 2 diabetes is associated with pulmonary cavitation in men with HIV-TB coinfection.

Frontiers in endocrinology·2026

Same author

Robust Bi<sup>3+</sup>-Eu<sup>3+</sup> Co-doped olivine-type phosphor for optical thermometry: High sensitivity and pH resistance.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2025

Same author

Nutritional risk and HbA1c as critical risk factors and predictors of opportunistic infections in HIV-DM comorbid patients: a retrospective cross-sectional study.

Frontiers in endocrinology·2025

Same author

The Role and Mechanism of Spinal NF-κB-CXCL1/CXCR2 in Rats with Nucleus Pulposus-induced Radicular Pain.

Spine·2023

Same author

How immune breakthroughs could slow disease progression and improve prognosis in COVID-19 patients: a retrospective study.

Frontiers in immunology·2023

Same author

Nutritional risk and a high NRS2002 score are closely related to disease progression and poor prognosis in patients with COVID-19.

Frontiers in nutrition·2023

Search research articles

Related Experiment Video

Updated: May 13, 2026

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

Res-NeuS: Deep Residuals and Neural Implicit Surface Learning for Multi-View Reconstruction.

Wei Wang^1,2, Fengjiao Gao¹, Yongliang Shen²

¹Intelligent Manufacturing Institute, Heilongjiang Academy of Sciences, Harbin 150090, China.

Sensors (Basel, Switzerland)

|February 10, 2024

Summary

Res-NeuS enhances 3D surface reconstruction for large-scale scenes using ResNet-50 and neural surface rendering. This method significantly improves detail capture and accuracy compared to existing approaches.

Keywords:

ResNet-50 appearance embedding neural radiance field rendering surface reconstruction

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Related Experiment Videos

Last Updated: May 13, 2026

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Area of Science:

Computer Vision
3D Reconstruction
Deep Learning

Background:

Neural rendering effectively reconstructs 3D surfaces from images.
Current methods struggle with large-scale scenes due to view sparsity and complexity.

Purpose of the Study:

To present Res-NeuS, a novel method for high-fidelity dense 3D reconstruction in complex, large-scale scenes.
To improve the handling of intricate details and geometric ambiguity in 3D surface reconstruction.

Main Methods:

ResNet-50 extracts appearance depth features for enhanced detail capture.
Point interpolation and weight optimization for accurate surface localization.
Photometric consistency and geometric constraints refine 3D surfaces.
Automatic 3D geometry sampling enables coarse-to-fine reconstruction.

Main Results:

Res-NeuS demonstrates superior performance in reconstructing complex, large-scale 3D scenes.
Achieved a harmful distance 0.4x lower than general neural rendering methods.
Achieved a harmful distance 0.6x lower than traditional 3D reconstruction methods.

Conclusions:

Res-NeuS effectively addresses limitations of current neural rendering techniques for large-scale 3D reconstruction.
The method significantly enhances the fidelity and accuracy of reconstructed 3D models.