2024年9月27日 · Inspired by this, we propose a novel diffusion-based approach (namely Center-based Semi-hard Synthetic Face Generation (CemiFace)) which produces facial samples with various levels of similarity to the subject center, thus allowing to generate face datasets containing effective discriminative samples for training face recognition.

In this paper, we learns 3D face representations from unconstrained photo collections without constrained by a linear 3DMM. We propose a novel encoder-decoder archi-tecture using inverse rendering that bridges computer vi-sion and computer graphics techniques.

To address these challenges, we propose an unsupervised learning framework based on CycleGAN, named Semi-Cycled GAN (SMC-GAN), designed specifically for large-pose face frontalization. This model leverages unpaired datasets, which enhances its generalization capability across diverse face images.

2022年12月18日 · To overcome these difficulties, we propose a novel framework termed Mask-FPAN. It uses a de-occlusion module that learns to parse occluded faces in a semi-supervised way. In particular, face landmark localization, face occlusionstimations, and detected head poses are taken into account.

2019年10月27日 · To tackle this problem, we propose a semi-supervised monocular reconstruction method, which jointly optimizes a shape-preserved domain-transfer CycleGAN and a shape estimation network. The framework is semi-supervised trained with 3D rendered images with ground-truth shapes and in-the-wild face images without any extra annotation.

4 天之前 · Facial expression recognition (FER) continues to be a vibrant research field, driven by the increasing need for its practical applications in areas such as e-learning, healthcare, candidate interview analysis, and more. Most deep learning approaches in supervised FER systems heavily rely on large, labeled datasets. Implementing FER in Convolutional Neural Networks (CNNs) often requires many ...

2020年9月21日 · To train a frontalization network which generalizes well to both constrained and unconstrained environments, we propose a semi-supervised learning framework which effectively uses both (labeled) indoor and (unlabeled) outdoor faces.

Inspired by this, we propose a novel diffusion-based approach (namely Center-based Semi-hard Synthetic FaceGeneration (CemiFace) which produces facial samples with various levels of similarity to the subject center, thus allowing to generate face datasets containing effective discriminative samples for training face recognition. Experimental ...

2020年9月14日 · To overcome this limitation, we propose in this paper a new generative adversarial network (named OA-GAN) for natural face de-occlusion without an occlusion mask, enabled by learning in a semi-supervised fashion using (i) paired images with known masks of artificial occlusions and (ii) natural images without occlusion masks.

We propose a novel diffusion-based model CemiFace that can generate face images with various levels of similarity to the identity center, which can be further applied to generate infinite center-based semi-hard face images for SFR.