Publications

Parametric models of the human head are essential tools in computer vision, graphics, and generative AI. We introduce the Generative aNthropometric Model (GNM), a comprehensive 3D head model...

From calibrated multi-view images, SHELLS reconstructs 18k-vertex 3D heads in 0.08 seconds. It aggregates DinoV2 features via projective surface-aware feature sampling, allowing a transformer to predict dense semantic...

We present CUBE (Control-based Unified B-spline Encoding), a new geometric representation for human faces that combines B-spline volumes with learned features, and demonstrate its use as a decoder...

In this work, we present a new method for multimodal conditional 3D face geometry generation that allows user-friendly control over the output identity and expression via a number...

In this work, we propose to jointly learn the visual appearance and depth of faces simultaneously in a diffusion-based portrait image generator. Our method embraces the end-to-end diffusion...

In this work, we present a new method for reconstructing the appearance properties of human faces from a lightweight capture procedure in an unconstrained environment.

In this work, we propose to couple locally-defined facial expressions with 3D Gaussian splatting to enable creating ultra-high fidelity, expressive and photorealistic head avatars.

We address the practical problem of generating facial blendshapes and reference animations for a new 3D character in production environments.

We introduce Spline-based Transformers, a new class of transformer models that do not require position encoding.

In this work, we aim to make physics-based facial animation more accessible by proposing a generalized physical face model that we learn from a large 3D face dataset....

In this work, we examine 3 important issues in the practical use of state-of-the-art facial landmark detectors and show how a combination of specific architectural modifications can directly...

In this work, we simultaneously tackle both the motion and illumination problem, proposing a new method for relightable and animatable neural heads.

In this work, we present a novel use case for such implicit representations in the context of learning anatomically constrained face models.

We present a new method to animate the dynamic motion of skin micro wrinkles under facial expression deformation.

In this work we aim to overcome the gap between synthetic simulation and real skin scanning, by proposing a method that can be applied to large skin regions...

We propose a new face model based on a data-driven implicit neural physics model that can be driven by both expression and style separately. At the core, we...

In this work, we propose a new loss function for monocular face capture, inspired by how humans would perceive the quality of a 3D face reconstruction given a...

In this paper, we target the application scenario of capturing high-fidelity assets for neural relighting in controlled studio conditions, but without requiring a dense light stage. Instead, we...

We present a novel graph-based simulation approach for generating micro wrinkle geometry on human skin, which can easily scale up to the micro-meter range and millions of wrinkles....

We propose the first facial landmark detection network that can predict continuous, unlimited landmarks, allowing to specify the number and location of the desired landmarks at inference time....

We demonstrate how the simple U-Net, surprisingly, allows us to advance the state of the art for re-aging real faces on video, with unprecedented temporal stability and preservation...

We approach the problem of face swapping from the perspective of learning simultaneous convolutional facial autoencoders for the source and target identities, using a shared encoder network with...

We propose a 3D+time framework for modeling dynamic sequences of 3D facial shapes, representing realistic non-rigid motion during a performance.

We demonstrate how MoRF is a strong new step towards 3D morphable neural head modeling.

We demonstrate the proposed capture pipeline on a variety of different facial hair styles and lengths, ranging from sparse and short to dense full-beards.

We present a new method for high-fidelity offline facial performance retargeting that is neither expensive nor artifact-prone.

We compare the results obtained with a state-of-the-art appearance capture method, with and without our proposed improvements to the lighting model.

We present a new nonlinear parametric 3D shape model based on transformer architectures.

We propose to combine incomplete, high-quality renderings showing only facial skin with recent methods for neural rendering of faces, in order to automatically and seamlessly create photo-realistic full-head...

We propose Adaptive convolutions; a generic extension of AdaIN, which allows for the simultaneous transfer of both statistical and structural styles in real time.

We present a method for nonlinear 3D face modeling using neural architectures.

Facial landmark detection is a fundamental task for many consumer and high-end applications and is almost entirely solved by machine learning methods today.

Road segmentation and tracking is of prime importance in Advanced Driver Assistance Systems (ADAS) to either assist autonomous navigation or provide useful information to drivers operating semi-autonomous vehicles....

This paper proposes a method to segment the exudates and lesions in retinal fundus images and classify using selective brightness feature. [[Paper]](https://ieeexplore.ieee.org/abstract/document/6141299)