Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Recent Advancement in 3D Biometrics using Monocular Camera

Aritra Mukherjee, Abhijit Das

TL;DR

The paper surveys recent advances in 3D biometrics using monocular vision, highlighting how single-camera depth cues can approximate 3D information traditionally obtained with expensive sensors. It analyzes techniques across modalities—especially 3D face reconstruction via pseudo-depth maps, 3D morphable models, and neural field approaches such as NeRF—alongside vein, gait, and eye-movement biometrics, commercial solutions, and anti-spoofing. It also enumerates open research problems, including lighting-invariant depth reconstruction, bias mitigation, generalization across sensors and traits, and explainability. The findings underscore the practical potential of affordable, scalable monocular 3D biometric systems while identifying key hurdles to robust, real-world deployment.

Abstract

Recent literature has witnessed significant interest towards 3D biometrics employing monocular vision for robust authentication methods. Motivated by this, in this work we seek to provide insight on recent development in the area of 3D biometrics employing monocular vision. We present the similarity and dissimilarity of 3D monocular biometrics and classical biometrics, listing the strengths and challenges. Further, we provide an overview of recent techniques in 3D biometrics with monocular vision, as well as application systems adopted by the industry. Finally, we discuss open research problems in this area of research

Recent Advancement in 3D Biometrics using Monocular Camera

TL;DR

The paper surveys recent advances in 3D biometrics using monocular vision, highlighting how single-camera depth cues can approximate 3D information traditionally obtained with expensive sensors. It analyzes techniques across modalities—especially 3D face reconstruction via pseudo-depth maps, 3D morphable models, and neural field approaches such as NeRF—alongside vein, gait, and eye-movement biometrics, commercial solutions, and anti-spoofing. It also enumerates open research problems, including lighting-invariant depth reconstruction, bias mitigation, generalization across sensors and traits, and explainability. The findings underscore the practical potential of affordable, scalable monocular 3D biometric systems while identifying key hurdles to robust, real-world deployment.

Abstract

Recent literature has witnessed significant interest towards 3D biometrics employing monocular vision for robust authentication methods. Motivated by this, in this work we seek to provide insight on recent development in the area of 3D biometrics employing monocular vision. We present the similarity and dissimilarity of 3D monocular biometrics and classical biometrics, listing the strengths and challenges. Further, we provide an overview of recent techniques in 3D biometrics with monocular vision, as well as application systems adopted by the industry. Finally, we discuss open research problems in this area of research
Paper Structure (14 sections, 2 figures, 5 tables)

This paper contains 14 sections, 2 figures, 5 tables.

Table of Contents

  1. Introduction
  2. 3D biometrics with monocular vision
  3. Benefits
  4. Challenges
  5. Recent advancement on 3D biometrics with monocular vision
  6. Face biometrics
  7. Vein pattern biometrics
  8. Gait biometrics
  9. Eye movement biometric
  10. Other available works
  11. Commercial solutions
  12. Summary
  13. Open research problems
  14. Conclusions

Figures (2)

  • Figure 1: Graph of scientific papers published per year in the period 1998-2022 matching keywords including “3D biometrics” and "single camera monocular vision”. From Scopus (https://www.scopus.com).
  • Figure 2: Relationship between sensor hardware, biometric traits and applications and methodologies used for them, as per recent development in the field.