We present the first neural relighting approach for rendering high-fidel...
Photorealistic avatars of human faces have come a long way in recent yea...
Photorealistic telepresence requires both high-fidelity body modeling an...
Despite recent progress in developing animatable full-body avatars, real...
Virtual telepresence is the future of online communication. Clothing is ...
We present a learning-based method for building driving-signal aware
ful...
This paper presents a generic method for generating full facial 3D anima...
Telecommunication with photorealistic avatars in virtual or augmented re...
3D video avatars can empower virtual communications by providing compres...
Real-time rendering and animation of humans is a core function in games,...
We present Supervision by Registration and Triangulation (SRT), an
unsup...
Codec Avatars are a recent class of learned, photorealistic face models ...
Bundle adjustment jointly optimizes camera intrinsics and extrinsics and...
Learning latent representations of registered meshes is useful for many ...
We present a data-driven approach for 4D space-time visualization of dyn...
Non verbal behaviours such as gestures, facial expressions, body posture...
We present the first single-network approach for 2D whole-body pose
esti...
Modeling and rendering of dynamic scenes is challenging, as natural scen...
We introduce a data-driven approach for interactively synthesizing
in-th...
We present a new research task and a dataset to understand human social
...
We present LBS-AE; a self-supervised autoencoding algorithm for fitting
...
Realtime multi-person 2D pose estimation is a key component in enabling
...
We present a method to combine markerless motion capture and dense pose
...
We present the first method to capture the 3D total motion of a target p...
We present an online approach to efficiently and simultaneously detect a...
We introduce a data-driven approach for unsupervised video retargeting t...
We introduce a deep appearance model for rendering the human face. Inspi...
In this paper, we present supervision-by-registration, an unsupervised
a...
Reliable markerless motion tracking of multiple people participating in
...
This paper proposes a new method for Non-Rigid Structure-from-Motion (NR...
We present a unified deformation model for the markerless capture of mul...
We present a simple nearest-neighbor (NN) approach that synthesizes
high...
We present an approach to capture the 3D motion of a group of people eng...
We present an approach to efficiently detect the 2D pose of multiple peo...
Data seems cheap to get, and in many ways it is, but the process of crea...
Pose Machines provide a sequential prediction framework for learning ric...