Research

We present a system that animates children’s drawings of the human figure, is robust to the variance inherent in these depictions, and is simple enough for anyone to use.

We present a method for reproducing complex multi-character interactions for physically simulated humanoid characters using deep reinforcement learning.

Focus on the underexplored question of how to personalize these systems while preserving privacy.

Meta deploys large-scale distributed storage services across datacenters. Storage applications are often categorized based on the type and temperature of the data stored: hot, ...

Proposing Point Straight Flow, a model that exhibits impressive performance using one step.

Propose a framework based on diffusion models for consistent and realistic long-term novel view synthesis. Diffusion models have achieved impressive performance on many content creation applications, such as image-to-image translation and text-to- image generation.

we introduce an alternative formulation called “user-centric ranking” based on a transposed view, which casts ‘users’ as ‘tokens’ and ‘items’ as ‘documents’ instead. We show that this formulation has a number of advantages and shows less sign of quality saturation when trained on substantially larger data sets.

We present the design of a productionized end-to-end stereo depth sensing system that does pre-processing, online stereo rectification, and stereo depth estimation with...

We introduce RoDynRF, an algorithm for reconstructing dynamic radiance fields from casual videos. Unlike existing approaches, we do not require accurate camera poses as input. Our method optimizes camera poses and two radiance fields, modeling static and dynamic elements. Our approach includes a coarse-to-fine strategy and epipolar geometry to exclude moving pixels, deformation fields, time- dependent appearance models, and regularization losses for improved consistency.

In this work, we present a fully binarized distance computing (BinDC) framework to perform distance computations for few-shot learning using only accumulation and logic operations.