Related papers: 3D Face Modeling via Weakly-supervised Disentangle…

Face animation is a challenging task. Existing model-based methods (utilizing 3DMMs or landmarks) often result in a model-like reconstruction effect, which doesn't effectively preserve identity. Conversely, model-free approaches face…

Face image manipulation via three-dimensional guidance has been widely applied in various interactive scenarios due to its semantically-meaningful understanding and user-friendly controllability. However, existing 3D-morphable-model-based…

Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and pose information. In this work, we aim at generating such…

We propose a novel 3D deepfake generation framework based on 3D Gaussian Splatting that enables realistic, identity-preserving face swapping and reenactment in a fully controllable 3D space. Compared to conventional 2D deepfake approaches…

A large part of the literature on learning disentangled representations focuses on variational autoencoders (VAE). Recent developments demonstrate that disentanglement cannot be obtained in a fully unsupervised setting without inductive…

Domain generalization aims to learn an invariant model that can generalize well to the unseen target domain. In this paper, we propose to tackle the problem of domain generalization by delivering an effective framework named Variational…

We propose a novel approach to disentangle the generative factors of variation underlying a given set of observations. Our method builds upon the idea that the (unknown) low-dimensional manifold underlying the data space can be explicitly…

Blind face restoration endeavors to restore a clear face image from a degraded counterpart. Recent approaches employing Generative Adversarial Networks (GANs) as priors have demonstrated remarkable success in this field. However, these…

Limited annotated data available for the recognition of facial expression and action units embarrasses the training of deep networks, which can learn disentangled invariant features. However, a linear model with just several parameters…

Face anti-spoofing (FAS) techniques aim to enhance the security of facial identity authentication by distinguishing authentic live faces from deceptive attempts. While two-class FAS methods risk overfitting to training attacks to achieve…

Confounding bias is a crucial problem when applying machine learning to practice, especially in clinical practice. We consider the problem of learning representations independent to multiple biases. In literature, this is mostly solved by…

Speaker verification, as a biometric authentication mechanism, has been widely used due to the pervasiveness of voice control on smart devices. However, the task of "in-the-wild" speaker verification is still challenging, considering the…

Face anti-spoofing is crucial to security of face recognition systems. Previous approaches focus on developing discriminative models based on the features extracted from images, which may be still entangled between spoof patterns and real…

Disentangled generative models map a latent code vector to a target space, while enforcing that a subset of the learned latent codes are interpretable and associated with distinct properties of the target distribution. Recent advances have…

A good feature representation is the key to image classification. In practice, image classifiers may be applied in scenarios different from what they have been trained on. This so-called domain shift leads to a significant performance drop…

We propose DiscoFaceGAN, an approach for face image generation of virtual people with disentangled, precisely-controllable latent representations for identity of non-existing people, expression, pose, and illumination. We embed 3D priors…

Disentangling the underlying feature attributes within an image with no prior supervision is a challenging task. Models that can disentangle attributes well provide greater interpretability and control. In this paper, we propose a…

Deep learning vision models excel with abundant supervision, but many applications face label scarcity and class imbalance. Controllable image editing can augment scarce labeled data, yet edits often introduce artifacts and entangle…

Designing realistic digital humans is extremely complex. Most data-driven generative models used to simplify the creation of their underlying geometric shape do not offer control over the generation of local shape attributes. In this paper,…

Here we propose a novel model family with the objective of learning to disentangle the factors of variation in data. Our approach is based on the spike-and-slab restricted Boltzmann machine which we generalize to include higher-order…