Generative Reality Lab

Meet the incredible individuals that make our organization thrive. Each member brings a unique set of skills, expertise, and passion to the table, united by a common goal: to deliver excellence in everything we do. Meet the incredible individuals that make our organization thrive. Each member brings a unique set of skills, expertise, and passion to the table, united by a common goal: to deliver excellence in everything we do.Meet the incredible individuals that make our organization thrive. Each member brings a unique set of skills, expertise, and passion to the table, united by a common goal: to deliver excellence in everything we do.

2021 | Authored by : Jiaman Li, Ruben Villegas, Duygu Ceylan, Jimei Yang, Zhengfei Kuang, Hao Li, Yajie Zhao

TASK-GENERIC HIERARCHICAL HUMAN MOTION PRIOR USING VAES

2020 | Authored by : Shichen Liu, Tianye Li, Weikai Chen, Hao Li

Generative Reality Lab

TASK-GENERIC HIERARCHICAL HUMAN MOTION PRIOR USING VAES

TASK-GENERIC HIERARCHICAL HUMAN MOTION PRIOR USING VAES

A GENERAL DIFFERENTIABLE MESH RENDERER FOR IMAGE-BASED 3D REASONING

A GENERAL DIFFERENTIABLE MESH RENDERER FOR IMAGE-BASED 3D REASONING

PLENOCTREES FOR REAL-TIME RENDERING OF NEURAL RADIANCE FIELDS

PLENOCTREES FOR REAL-TIME RENDERING OF NEURAL RADIANCE FIELDS

TOPOLOGICALLY CONSISTENT MULTI-VIEW FACE INFERENCE USING VOLUMETRIC SAMPLING

TOPOLOGICALLY CONSISTENT MULTI-VIEW FACE INFERENCE USING VOLUMETRIC SAMPLING

MONOCULAR REAL-TIME VOLUMETRIC PERFORMANCE CAPTURE

MONOCULAR REAL-TIME VOLUMETRIC PERFORMANCE CAPTURE

DISUNKNOWN: DISTILLING UNKNOWN FACTORS FOR DISENTANGLEMENT LEARNING

DISUNKNOWN: DISTILLING UNKNOWN FACTORS FOR DISENTANGLEMENT LEARNING

NORMALIZED AVATAR SYNTHESIS USING STYLEGAN AND PERCEPTUAL REFINEMENT

NORMALIZED AVATAR SYNTHESIS USING STYLEGAN AND PERCEPTUAL REFINEMENT

DYNAMIC FACIAL ASSET AND RIG GENERATION FROM A SINGLE SCAN

DYNAMIC FACIAL ASSET AND RIG GENERATION FROM A SINGLE SCAN

FULLY CONVOLUTIONAL MESH AUTOENCODER USING EFFICIENT SPATIALLY VARYING KERNELS

FULLY CONVOLUTIONAL MESH AUTOENCODER USING EFFICIENT SPATIALLY VARYING KERNELS

EQUIVARIANT POINT NETWORK FOR 3D POINT CLOUD ANALYSIS

EQUIVARIANT POINT NETWORK FOR 3D POINT CLOUD ANALYSIS

LEARNING FORMATION OF PHYSICALLY-BASED FACE ATTRIBUTES

LEARNING FORMATION OF PHYSICALLY-BASED FACE ATTRIBUTES

INTUITIVE, INTERACTIVE BEARD AND HAIR SYNTHESIS WITH GENERATIVE MODELS

INTUITIVE, INTERACTIVE BEARD AND HAIR SYNTHESIS WITH GENERATIVE MODELS

ARCH: ANIMATABLE RECONSTRUCTION OF CLOTHED HUMANS

ARCH: ANIMATABLE RECONSTRUCTION OF CLOTHED HUMANS

LEARNING TO INFER IMPLICIT SURFACES WITHOUT 3D SUPERVISION

LEARNING TO INFER IMPLICIT SURFACES WITHOUT 3D SUPERVISION

DEEP FACE NORMALIZATION

DEEP FACE NORMALIZATION

TRANSFORMABLE BOTTLENECK NETWORKS

TRANSFORMABLE BOTTLENECK NETWORKS

LEARNING PERSPECTIVE UNDISTORTION OF PORTRAITS

LEARNING PERSPECTIVE UNDISTORTION OF PORTRAITS

PIFU: PIXEL-ALIGNED FUNCTION FOR HIGH-RESOLUTION CLOTHED HUMAN DIGITIZATION

PIFU: PIXEL-ALIGNED FUNCTION FOR HIGH-RESOLUTION CLOTHED HUMAN DIGITIZATION

SOFTRASTERIZER: DIFFERENTIABLE RENDERING FOR IMAGE-BASED 3D REASONING

SOFTRASTERIZER: DIFFERENTIABLE RENDERING FOR IMAGE-BASED 3D REASONING

HAIRBRUSH FOR IMMERSIVE DATA-DRIVEN HAIR MODELING

HAIRBRUSH FOR IMMERSIVE DATA-DRIVEN HAIR MODELING

PROTECTING WORLD LEADERS AGAINST DEEP FAKES

PROTECTING WORLD LEADERS AGAINST DEEP FAKES

SICLOPE: SILHOUETTE-BASED CLOTHED PEOPLE

SICLOPE: SILHOUETTE-BASED CLOTHED PEOPLE

ON THE CONTINUITY OF ROTATION REPRESENTATION IN NEURAL NETWORKS

ON THE CONTINUITY OF ROTATION REPRESENTATION IN NEURAL NETWORKS

DEEP VOLUMETRIC VIDEO FROM VERY SPARSE MULTI-VIEW PERFORMANCE CAPTURE

DEEP VOLUMETRIC VIDEO FROM VERY SPARSE MULTI-VIEW PERFORMANCE CAPTURE

HAIRNET: SINGLE-VIEW HAIR RECONSTRUCTION USING CONVOLUTIONAL NEURAL NETWORKS

HAIRNET: SINGLE-VIEW HAIR RECONSTRUCTION USING CONVOLUTIONAL NEURAL NETWORKS

REAL-TIME HAIR RENDERING USING SEQUENTIAL ADVERSARIAL NETWORKS

REAL-TIME HAIR RENDERING USING SEQUENTIAL ADVERSARIAL NETWORKS

3D HAIR SYNTHESIS USING VOLUMETRIC VARIATIONAL AUTOENCODERS

3D HAIR SYNTHESIS USING VOLUMETRIC VARIATIONAL AUTOENCODERS

PAGAN: REAL-TIME AVATARS USING DYNAMIC TEXTURES

PAGAN: REAL-TIME AVATARS USING DYNAMIC TEXTURES

TECHNICAL PERSPECTIVE: PHOTOREALISTIC FACIAL DIGITIZATION AND MANIPULATION

TECHNICAL PERSPECTIVE: PHOTOREALISTIC FACIAL DIGITIZATION AND MANIPULATION

HYBRID FUSION: REAL-TIME PERFORMANCE CAPTURE USING A SINGLE DEPTH SENSOR AND SPARSE IMUS

HYBRID FUSION: REAL-TIME PERFORMANCE CAPTURE USING A SINGLE DEPTH SENSOR AND SPARSE IMUS

CONTEXTUAL-BASED IMAGE INPAINTING: INFER, MATCH, AND TRANSLATE

CONTEXTUAL-BASED IMAGE INPAINTING: INFER, MATCH, AND TRANSLATE

HIGH-FIDELITY FACIAL REFLECTANCE AND GEOMETRY INFERENCE FROM AN UNCONSTRAINED IMAGE

HIGH-FIDELITY FACIAL REFLECTANCE AND GEOMETRY INFERENCE FROM AN UNCONSTRAINED IMAGE

MESOSCOPIC FACIAL GEOMETRY INFERENCE USING DEEP NEURAL NETWORKS

MESOSCOPIC FACIAL GEOMETRY INFERENCE USING DEEP NEURAL NETWORKS

DOUBLE FUSION: REAL-TIME CAPTURE OF HUMAN PERFORMANCES WITH INNER BODY SHAPES FROM A SINGLE DEPTH SENSOR

DOUBLE FUSION: REAL-TIME CAPTURE OF HUMAN PERFORMANCES WITH INNER BODY SHAPES FROM A SINGLE DEPTH SENSOR

REAL-TIME FACIAL SEGMENTATION AND PERFORMANCE CAPTURE FROM RGB INPUT

REAL-TIME FACIAL SEGMENTATION AND PERFORMANCE CAPTURE FROM RGB INPUT

AUTO-CONDITIONED RECURRENT NETWORKS FOR EXTENDED COMPLEX HUMAN MOTION SYNTHESIS

AUTO-CONDITIONED RECURRENT NETWORKS FOR EXTENDED COMPLEX HUMAN MOTION SYNTHESIS

AVATAR DIGITIZATION FROM A SINGLE IMAGE FOR REAL-TIME RENDERING

AVATAR DIGITIZATION FROM A SINGLE IMAGE FOR REAL-TIME RENDERING

LEARNING A MODEL OF FACIAL SHAPE AND EXPRESSION FROM 4D SCANS

LEARNING A MODEL OF FACIAL SHAPE AND EXPRESSION FROM 4D SCANS

HIGH-FIDELITY FACIAL AND SPEECH ANIMATION FOR VR HMDS

HIGH-FIDELITY FACIAL AND SPEECH ANIMATION FOR VR HMDS

LEARNING DENSE FACIAL CORRESPONDENCES IN UNCONSTRAINED IMAGES