Explore the latest research from Facebook

We present a method for building high-fidelity animatable 3D face models that can be posed and rendered with novel lighting environments in real-time.

In this paper, we develop a learning framework that generates control policies for physically simulated athletes who have many degrees-of-freedom. Our framework uses a two step-approach, learning basic skills and learning boutlevel strategies, with deep reinforcement learning, which is inspired by the way that people how to learn competitive sports.

We present Mixture of Volumetric Primitives (MVP), a representation for rendering dynamic 3D content that combines the completeness of volumetric representations with the efficiency of primitive-based rendering, e.g., point-based or mesh-based methods. Our approach achieves this by leveraging spatially shared computation with a convolutional architecture and by minimizing computation in empty regions of space with volumetric primitives that can move to cover only occupied regions.

In this paper, we propose a hand-object spatial representation that can achieve generalization from limited data. Our representation combines the global object shape as voxel occupancies with local geometric details as samples of closest distances. This representation is used by a neural network to regress finger motions from input trajectories of wrists and objects.

In this work, we present the Pixel Codec Avatars (PiCA): a deep generative model of 3D human faces that achieves state of the art reconstruction performance while being computationally efficient and adaptive to the rendering conditions during execution.

Accurate estimation of 3D human motion from monocular video requires modeling both kinematics (body motion without physical forces) and dynamics (motion with physical forces).

This paper describes the application of two methods for ear-aligned HRTF interpolation by sparse sampling: Orthogonal Matching Pursuit and Principal Component Analysis.

This work presents a preliminary attempt to blindly estimate reflection amplitudes. An iterative estimator is suggested, based on maximum likelihood and alternating least squares.

In this paper, we introduce a different research direction by viewing each audio channel as a node lying in a non-Euclidean space and, specifically, a graph.

Using 3D ear shapes as inputs, we explore the bounds of HRTF predictability using deep neural networks. To that end, we propose and evaluate two models, and identify the lowest achievable spectral distance error when predicting the true HRTF magnitude spectra.