Supplementary Material : GANFIT : Generative Adversarial Network Fitting for High Fidelity 3 D Face Reconstruction

In order to evaluate identity preservation capacity of the proposed method, we run two face recognition experiments on Labelled Faces in the Wild (LFW) dataset [2]. Following [1], we feed real LFW images and rendered images of their 3D reconstruction by our method to a pretrained face recognition network, namely VGG-Face[3]. We then compute the activations at the embedding layer and measure cosine similarity between 1) real and rendered images and 2) renderings of same/different pairs.