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

Survival Tree

Survival Tree

Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...

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

Comparative study of histological differences according to monopolar radiofrequency tip width.

Lasers in medical science·2026

Same author

High-titer retinal production in Yarrowia lipolytica via redox engineering coupled with intra- and extracellular sequestration.

Bioresource technology·2026

Same author

Discrepancy-Guided Complementary Fusion for Unsupervised Multimodal Anomaly Detection.

Sensors (Basel, Switzerland)·2026

Same author

Weighted knowledge distillation for semi-supervised segmentation of maxillary sinus in panoramic X-ray images.

Scientific reports·2026

Same author

Position-wise comparison of handheld 6-lead ECG versus the standard 12-lead ECG in patients with arrhythmia: comparative study.

BMC cardiovascular disorders·2026

Same author

Spatial assessment of heat risk from deregulation of greenbelt in Seoul, South Korea.

Scientific reports·2026

Search research articles

Related Experiment Video

Updated: Jul 11, 2025

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

Knowledge distillation of multi-scale dense prediction transformer for self-supervised depth estimation.

Jimin Song¹, Sang Jun Lee²

¹Division of Electronic Engineering, Jeonbuk National University, 567 Baekje-daero Deokjin-gu, Jeonju, 54896, Korea.

Scientific Reports

|November 3, 2023

Summary

This study introduces a novel knowledge distillation method to improve self-supervised depth estimation. By using direct depth cues, the performance gap between supervised and self-supervised approaches is significantly reduced.

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Jul 11, 2025

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

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Computer Vision
Machine Learning
Deep Learning

Background:

Depth estimation from single images is crucial for various applications.
Supervised methods require external sensors for ground truth, limiting their practicality.
Self-supervised methods avoid ground truth data but lag in performance compared to supervised methods.

Purpose of the Study:

To bridge the performance gap between supervised and self-supervised depth estimation.
To develop a more effective training strategy for self-supervised depth networks.
To leverage direct depth cues for improved accuracy.

Main Methods:

Employed knowledge distillation (teacher-student framework) to transfer knowledge.
Trained a teacher network using self-supervised photometric error.
Developed a multi-scale dense prediction transformer with Monte Carlo dropout.
Proposed a multi-scale distillation loss using ensemble of stochastic estimates.

Main Results:

Achieved state-of-the-art accuracy in self-supervised depth estimation.
Demonstrated the effectiveness of direct depth cues over photometric errors.
Validated performance on KITTI and Make3D datasets.

Conclusions:

Knowledge distillation with direct depth cues enhances self-supervised depth estimation.
The proposed multi-scale distillation loss improves network training.
This approach offers a promising direction for practical single-image depth estimation.