Representing human performance at high-fidelity is an essential building...
We present a new method for lightweight novel-view synthesis that genera...
In this work, we advance the neural head avatar technology to the megapi...
We present a system for realistic one-shot mesh-based human head avatars...
Representing scenes with multiple semi-transparent colored layers has be...
Existing image generator networks rely heavily on spatial convolutions a...
Tensor networks are the main building blocks in a wide variety of
comput...
Modeling daytime changes in high resolution photographs, e.g., re-render...
We propose a Reinforcement Learning based approach to approximately solv...