Menglei Chai

Menglei Chai

Research Scientist

AR Perception, Google Inc.

Bio

I am a Research Scientist at Google AR Perception.
I was a Lead Research Scientist in the Creative Vision group at Snap Research.
I got my Ph.D. degree from the Graphics & Parallel Systems Lab (GAPS), Zhejiang University in 2017, supervised by Professor Kun Zhou.
My research interests lie at the intersection between Computer Vision and Computer Graphics, especially human digitization, image manipulation, 3D acquisition, and physics-based animation.

I am looking for self-motivated interns in CV&CG. Drop me an email if you are interested.

Interests

  • Human Digitization
  • Image Manipulation
  • 3D Reconstruction
  • Physics-Based Animation

Education

  • PhD in Computer Science, 2017

    Zhejiang University

  • BSc in Computer Science, 2011

    Zhejiang University

Publications

GroomCap: High-Fidelity Prior-Free Hair Capture

ACM Transactions on Graphics (SIGGRAPH Asia) 2024

MagicMirror: Fast and High-Quality Avatar Generation with a Constrained Search Space

European Conference on Computer Vision (ECCV) 2024

MVDD: Multi-View Depth Diffusion Models

European Conference on Computer Vision (ECCV) 2024

Chat2Layout: Interactive 3D Furniture Layout with a Multimodal LLM

Arxiv 2024

Efficient 3D Articulated Human Generation with Layered Surface Volumes

International Conference on 3D Vision (3DV) 2024

GroomGen: A High-Quality Generative Hair Model Using Hierarchical Latent Representations

ACM Transactions on Graphics (SIGGRAPH Asia) 2023

AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control

IEEE/CVF International Conference on Computer Vision (ICCV) 2023

InfiniCity: Infinite-Scale City Synthesis

IEEE/CVF International Conference on Computer Vision (ICCV) 2023

Efficient Learning of Mesh-Based Physical Simulation with Bi-Stride Multi-Scale Graph Neural Network

International Conference on Machine Learning (ICML) 2023

DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023

3DAvatarGAN: Bridging Domains for Personalized Editable Avatars

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023

Unsupervised Volumetric Animation

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023

Invertible Neural Skinning

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023

NeRF-Art: Text-Driven Neural Radiance Fields Stylization

IEEE Transactions on Visualization and Computer Graphics (TVCG) 2023

Semantic Probability Distribution Modeling for Diverse Semantic Image Synthesis

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2022

Cross-Modal 3D Shape Generation and Manipulation

European Conference on Computer Vision (ECCV) 2022

R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis

European Conference on Computer Vision (ECCV) 2022

Quantized GAN for Complex Music Generation from Dance Videos

European Conference on Computer Vision (ECCV) 2022

NeROIC: Neural Rendering of Objects from Online Image Collections

ACM Transactions on Graphics (SIGGRAPH) 2022

CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022

Cross-Domain and Disentangled Face Manipulation with 3D Guidance

IEEE Transactions on Visualization and Computer Graphics (TVCG) 2022

DisUnknown: Distilling Unknown Factors for Disentanglement Learning

IEEE/CVF International Conference on Computer Vision (ICCV) 2021

Efficient Semantic Image Synthesis via Class-Adaptive Normalization

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2021

Diverse Semantic Image Synthesis via Probability Distribution Modeling

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021

Flow Guided Transformable Bottleneck Networks for Motion Retargeting

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021

Motion Representations for Articulated Animation

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021

A Good Image Generator Is What You Need for High-Resolution Video Synthesis

International Conference on Learning Representations (ICLR) 2021

Exemplar-Based 3D Portrait Stylization

IEEE Transactions on Visualization and Computer Graphics (TVCG) 2021

FaceBlit: Instant Real-Time Example-Based Style Transfer to Facial Videos

ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (i3D) 2021

Neural Hair Rendering

European Conference on Computer Vision (ECCV) 2020

MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait Editing

ACM Transactions on Graphics (SIGGRAPH) 2020

Interactive Video Stylization Using Few-Shot Patch-Based Training

ACM Transactions on Graphics (SIGGRAPH) 2020

Revisiting Image Aesthetic Assessment via Self-Supervised Feature Learning

AAAI Conference on Artificial Intelligence (AAAI) 2020

Real-Time Hair Simulation with Neural Interpolation

IEEE Transactions on Visualization and Computer Graphics (TVCG) 2020

Human Motion Transfer from Poses in the Wild

European Conference on Computer Vision Workshops (ECCVW) 2020

Learning to Assess Visual Aesthetics of Food Images

Computational Visual Media (CVM) 2020

End-to-End Time-Lapse Video Synthesis from a Single Outdoor Image

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019

Real-Time Patch-Based Stylization of Portraits Using Generative Adversarial Network

ACM/EG Expressive 2019

Stabilized Real-Time Face Tracking via a Learned Dynamic Rigidity Prior

ACM Transactions on Graphics (SIGGRAPH Asia) 2018

Parametric Weight-Change Reshaping for Portrait Images

IEEE Computer Graphics and Applications (CG&A) 2018

A Data-Driven Approach to Four-View Image-Based Hair Modeling

ACM Transactions on Graphics (SIGGRAPH) 2017

AutoHair: Fully Automatic Hair Modeling from a Single Image

ACM Transactions on Graphics (SIGGRAPH) 2016

Adaptive Skinning for Interactive Hair-Solid Simulation

IEEE Transactions on Visualization and Computer Graphics (TVCG) 2016

High-Quality Hair Modeling from a Single Portrait Photo

ACM Transactions on Graphics (SIGGRAPH Asia) 2015

A Reduced Model for Interactive Hairs

ACM Transactions on Graphics (SIGGRAPH) 2014

Cone Tracing for Furry Object Rendering

IEEE Transactions on Visualization and Computer Graphics (TVCG) 2014

Dynamic Hair Manipulation in Images and Videos

ACM Transactions on Graphics (SIGGRAPH) 2013

As-Rigid-As-Possible Distance Field Metamorphosis

Computer Graphics Forum (Pacific Graphics) 2013

Hair Interpolation for Portrait Morphing

Computer Graphics Forum (Pacific Graphics) 2013

Single-View Hair Modeling for Portrait Manipulation

ACM Transactions on Graphics (SIGGRAPH) 2012