Toward Better SSIM Loss for Unsupervised Monocular Depth Estimation

Yijun Cao; Fuya Luo; Yongjie Li

doi:10.1007/978-3-031-46305-1_7

ScienceGate Book Chapters

BOOK-CHAPTER

Toward Better SSIM Loss for Unsupervised Monocular Depth Estimation

Yijun Cao Fuya Luo Yongjie Li

Year: 2023 Lecture notes in computer science Pages: 81-92 Publisher: Springer Science+Business Media

DOI: 10.1007/978-3-031-46305-1_7

Get Full-Text PDF Get Analytical Report

Keywords:

Luminance Computer science Artificial intelligence Hyperparameter Similarity (geometry) Pattern recognition (psychology) Contrast (vision) Function (biology) Monocular Mean squared error Unsupervised learning Image (mathematics) Mathematics Statistics

Metrics

Cited By

2.14

FWCI (Field Weighted Citation Impact)

Refs

0.90

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Advanced Vision and Imaging

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Optical measurement and interference techniques

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Image Processing Techniques and Applications

Physical Sciences → Engineering → Media Technology

Toward Better SSIM Loss for Unsupervised Monocular Depth Estimation

Metrics

Citation History

Topics

Related Documents

Unsupervised monocular depth estimation with aggregating image features and wavelet SSIM (Structural SIMilarity) loss

Unsupervised monocular depth learning using self-teaching and contrast-enhanced SSIM loss

What makes the unsupervised monocular depth estimation (UMDE) model training better

Unsupervised Monocular Depth Estimation Based on Dual Attention Mechanism and Depth-Aware Loss

FG-Depth: Flow-Guided Unsupervised Monocular Depth Estimation