Facebook, Inc.

Meta Platforms, Inc.

Camille Couprie

Yann Andre Le Cun

Michael Fabien Mathieu

Peizhao Zhang

Oran Gafni

Thibault Michel Max Peyronel

Daniel Raynald David Haziza

Tao Xu

Onur Çelebi

Patrick Labatut

Maxime Mohamad Oquab

Pierre Stock

In one embodiment, a first device may receive, from a second device, a reference landmark map identifying locations of facial features of a user of the second device depicted in a reference image and a feature map, generated based on the reference image, representing an identity of the user. The first device may receive, from the second device, a current compressed landmark map based on a current image of the user and decompress the current compressed landmark map to generate a current landmark map. The first device may update the feature map based on a motion field generated using the reference landmark map and the current landmark map. The first device may generate scaling factors based on a normalization facial mask of pre-determined facial features of the user. The first device may generate an output image of the user by decoding the updated feature map using the scaling factors.

Systems and method for low bandwidth video-chat compression

In one embodiment, a method includes receiving a plurality of input frames of a video sequence associated with a time t, predicting, using a convolutional network, one or more future frames of the video sequence from the plurality of input frames, wherein the convolutional network is trained with randomly selected temporal sequences of a n&#xd7;m grid of pixels from the plurality of input frames exhibiting a threshold of optical flow. In addition, the training may comprise randomly selecting temporal sequences of a n&#xd7;m grid of pixels from the plurality of input frames exhibiting a threshold of optical flow.

Deep multi-scale video prediction

In one embodiment, a method includes receiving a plurality of input frames of a video sequence associated with a time t, training a convolutional network to predict one or more future frames of the video sequence from the plurality of input frames based on a generative model, and outputting a first future frame of the video sequence associated with a time t+1 as predicted by the generative model. The training may comprise using an adversarial model and an image gradient difference loss model. In addition, the training may comprise randomly selecting temporal sequences of a n&#xd7;m grid of pixels from the plurality of input frames exhibiting a threshold of optical flow.

Growing community of inventors

Montgeron, France

Camille Couprie