Inverting face embeddings with convolutional neural networks
This addresses the challenge of reconstructing images from compressed face representations, which is incremental as it builds on existing embedding and generation techniques.
The paper tackles the problem of inverting low-dimensional face embeddings to generate realistic, consistent images, showing that gradient ascent with a guiding image can produce such images and that a separate neural network can solve this minimization problem in real-time with minimal loss compared to gradient descent.
Deep neural networks have dramatically advanced the state of the art for many areas of machine learning. Recently they have been shown to have a remarkable ability to generate highly complex visual artifacts such as images and text rather than simply recognize them. In this work we use neural networks to effectively invert low-dimensional face embeddings while producing realistically looking consistent images. Our contribution is twofold, first we show that a gradient ascent style approaches can be used to reproduce consistent images, with a help of a guiding image. Second, we demonstrate that we can train a separate neural network to effectively solve the minimization problem in one pass, and generate images in real-time. We then evaluate the loss imposed by using a neural network instead of the gradient descent by comparing the final values of the minimized loss function.