DeepAI AI Chat
Log In Sign Up

Improving Face Detection Performance with 3D-Rendered Synthetic Data

by   Jian Han, et al.

In this paper, we provide a synthetic data generator methodology with fully controlled, multifaceted variations based on a new 3D face dataset (3DU-Face). We customized synthetic datasets to address specific types of variations (scale, pose, occlusion, blur, etc.), and systematically investigate the influence of different variations on face detection performances. We examine whether and how these factors contribute to better face detection performances. We validate our synthetic data augmentation for different face detectors (Faster RCNN, SSH and HR) on various face datasets (MAFA, UFDD and Wider Face).


page 3

page 4

page 7

page 8


Training Deep Face Recognition Systems with Synthetic Data

Recent advances in deep learning have significantly increased the perfor...

Improving DeepFake Detection Using Dynamic Face Augmentation

The creation of altered and manipulated faces has become more common due...

SynthASpoof: Developing Face Presentation Attack Detection Based on Privacy-friendly Synthetic Data

Recently, significant progress has been made in face presentation attack...

Privacy-friendly Synthetic Data for the Development of Face Morphing Attack Detectors

The main question this work aims at answering is: can morphing attack de...

Learning to mask: Towards generalized face forgery detection

Generalizability to unseen forgery types is crucial for face forgery det...

Unsupervised Face Recognition using Unlabeled Synthetic Data

Over the past years, the main research innovations in face recognition f...

Validating Seed Data Samples for Synthetic Identities – Methodology and Uniqueness Metrics

This work explores the identity attribute of synthetic face samples deri...