Controllable and Guided Face Synthesis for Unconstrained Face Recognition

07/20/2022
by   Feng Liu, et al.
10

Although significant advances have been made in face recognition (FR), FR in unconstrained environments remains challenging due to the domain gap between the semi-constrained training datasets and unconstrained testing scenarios. To address this problem, we propose a controllable face synthesis model (CFSM) that can mimic the distribution of target datasets in a style latent space. CFSM learns a linear subspace with orthogonal bases in the style latent space with precise control over the diversity and degree of synthesis. Furthermore, the pre-trained synthesis model can be guided by the FR model, making the resulting images more beneficial for FR model training. Besides, target dataset distributions are characterized by the learned orthogonal bases, which can be utilized to measure the distributional similarity among face datasets. Our approach yields significant performance gains on unconstrained benchmarks, such as IJB-B, IJB-C, TinyFace and IJB-S (+5.76

READ FULL TEXT

page 13

page 14

page 20

research
04/21/2019

Probabilistic Face Embeddings

Embedding methods have achieved success in face recognition by comparing...
research
04/14/2021

StEP: Style-based Encoder Pre-training for Multi-modal Image Synthesis

We propose a novel approach for multi-modal Image-to-image (I2I) transla...
research
08/19/2023

Controllable Multi-domain Semantic Artwork Synthesis

We present a novel framework for multi-domain synthesis of artwork from ...
research
02/26/2021

Mitigating Domain Mismatch in Face Recognition Using Style Matching

Despite outstanding performance on public benchmarks, face recognition s...
research
03/23/2023

Controllable Inversion of Black-Box Face-Recognition Models via Diffusion

Face recognition models embed a face image into a low-dimensional identi...
research
08/19/2018

GridFace: Face Rectification via Learning Local Homography Transformations

In this paper, we propose a method, called GridFace, to reduce facial ge...
research
07/05/2019

Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets

This paper targets the problem of image set-based face verification and ...

Please sign up or login with your details

Forgot password? Click here to reset