Facial reconstruction method based on non-supervision automatic encoder

Abstract

The invention provides a facial reconstruction method based on a non-supervision automatic encoder. The main content of the facial reconstruction method based on a non-supervision automatic encoder includes a semantic code vector, a decoder based on a parameter model and a loss layer. The process of the facial reconstruction method based on a non-supervision automatic encoder includes the steps: scene description is given in a semantic code vector mode; the parameter decoder generates a composite image corresponding the face, and a reverse image is formed through standard reverse propagation, and then end-to-end training without supervision is realized, and the parameter decoder includes an image forming model, a lighting model, image formation and reverse propagation; and a loss function is defined by three items, and the loss layer includes dense luminosity calibration, sparse landmark alignment, statistical regularization and reverse propagation. The facial reconstruction method based on a non-supervision automatic encoder can encode the details of the face, such as posture, shape, expression, skin color and scene lighting, is more exquisite, does not need supervision and allows end-to-end learning. Compared with a network of synthesizing face data training, the network can be preferably popularized to real data.

Description

technical field [0001] The invention relates to the field of face reconstruction, in particular to a face reconstruction method based on an unsupervised automatic encoder. Background technique [0002] One of the most important biological characteristics of the human body is the face, and face reconstruction is one of the hottest areas in the field of computer vision. Face reconstruction has broad practical applications, and has broad application prospects in the fields of face recognition systems, medicine, film advertisements, computer animation, games, video conferencing, video telephony, and human-computer interaction. In the field of public security, face reconstruction and recognition play an increasingly important role in public security criminal investigation and crime prevention, which cannot be ignored. In recent years, terrorist activities, violent incidents, violent crimes and other serious threats to public safety have frequently occurred. Face recognition can ...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems that facial posture, shape, expression, skin color and scene lighting will affect, the purpose of the present invention is to provide a face reconstruction method based on an unsupervised autoencoder, which provides a scene description in the form of semantic code vectors, parameters The decoder generates a synthetic image corresponding to the face, reverses the image formation by standard backpropagation, and realizes unsupervised end-to-end training, including image formation model, lighting model, image formation and backpropagation, and the loss is defined by three terms Functions, including dense photometric calibration, sparse landmark alignment, statistical regularization, and backpropagation

Images