Tianye Li

I am a Ph.D. candidate in Computer Science at USC, advised by Prof. Hao Li and Prof. Randall Hill, Jr. I also work in the Vision and Graphics Lab at USC Institute for Creative Technologies.

In summer and fall 2020, I was a research intern at the Facebook Reality Labs, hosted by Zhaoyang Lv. In summer 2018, I was a research intern at Snap Inc., working with Chongyang Ma and Linjie Luo. From fall 2016 to spring 2017, I visited the Max Planck Institute for Intelligent Systems (Tübingen), working with Timo Bolkart, Javier Romero, and Michael J. Black.

I did my B.Eng. at Xidian University and M.Sc. (with honor) at USC, both in Electrical Engineering, during which I had worked in Agilent Technologies (Keysight Technologies) and Dolby Laboratories.

Email: <first_name> <last_name> at protonmail dot com

CV  /  Google Scholar  /  Twitter

profile photo

My research interests are computer vision and computer graphics. Most of my work aim to capture and analyze the geometry, motion and appearance of dynamic and deformable objects, including human face and body as well as general objects and scenes.

cvpr22 Neural 3D Video Synthesis from Multi-view Video
Tianye Li*, Mira Slavcheva*, Michael Zollhoefer, Simon Green, Christoph Lassner, Changil Kim, Tanner Schmidt, Steven Lovegrove, Michael Goesele, Richard Newcombe, Zhaoyang Lv
CVPR 2022 (Oral Presentation)
paper / arxiv / project page / video / supplemental / data / poster / bibtex

A method that captures complex dynamic scenes and enables photorealistic 3D video synthesis from wide view angles and at arbitary times.

iccv21 Topologically Consistent Multi-View Face Inference Using Volumetric Sampling
Tianye Li, Shichen Liu, Timo Bolkart, Jiayi Liu, Hao Li, Yajie Zhao
ICCV 2021 (Oral Presentation)
paper / arxiv / code / project page / supplemental / video / talk / slides / poster / bibtex

We propose the ToFu framework that uses volumetric sampling to predict accurate base meshes in consistent topology directly from multi-view image inputs in only 0.385 seconds. ToFu also infers high-resolution skin appearance and detail maps, which enables photorealistic rendering.

tpami20 A General Differentiable Mesh Renderer for Image-based 3D Reasoning
Shichen Liu, Tianye Li, Weikai Chen, Hao Li
TPAMI 2020
paper / bibtex

An extended version of the Soft Rasterizer.

iccv19_softras Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning
Shichen Liu, Tianye Li, Weikai Chen, Hao Li
ICCV 2019 (Oral Presentation)
paper / code / poster / bibtex

A rasterization-based differentiable renderer for 3D meshes, Soft Rasterizer (SoftRas), that supports reasoning for geometry, texture, lighting conditions and camera poses with 2D images. An extended version of SoftRas has been incorporated into the PyTorch3D library.

iccv19_protrait_undist Learning Perspective Undistortion of Portraits
Yajie Zhao, Zeng Huang, Tianye Li, Weikai Chen, Chloe LeGendre, Xinglei Ren, Jun Xing, Ari Shapiro, Hao Li
ICCV 2019 (Oral Presentation)
paper / project page / bibtex

Given a face portrait, this system corrects the perspective distortion, easing subsequent facial recognition and reconstruction and reducing the bias for human perception.

eccv18 Deep Volumetric Video from Very Sparse Multi-view Performance Capture
Zeng Huang, Tianye Li, Weikai Chen, Yajie Zhao, Jun Xing, Chloe LeGendre, Linjie Luo, Chongyang Ma, Hao Li
ECCV 2018
paper / supplemental / video / poster / bibtex

Utilizing a learnt implicit representation for geometry, the method is able to capture dynamic performances of human actors with very sparse camera settings (3 or 4 views), which enables to high-quality volumetric videos.

sigasia17 Learning a Model of Facial Shape and Expression from 4D Scans
Tianye Li*, Timo Bolkart*, Michael J. Black, Hao Li, Javier Romero
SIGGRAPH Asia 2017
paper / supplemental / video / fast-forward / project page / model & data / bibtex

We propose a light-weight yet expressive generic face model, FLAME, by learning from large high-quality datasets and an appropriate separation of identity, expression and pose. The FLAME model has been incorporated into the SMPL-X model.

eccv16 Real-Time Facial Segmentation and Performance Capture from RGB Input
Shunsuke Saito, Tianye Li, Hao Li
ECCV 2016
paper / supplemental / arxiv / video / poster / data / bibtex

A real-time facial performance capture system from single RGB camera, that is robust to occlusion, thanks to an effective and real-time facial segmentation network.

reviewer Reviewer
  • CVPR (2020, 2021, 2022), ICCV (2019, 2021), ECCV (2020, 2022), SIGGRAPH (2022), SIGGRAPH Asia (2022), TPAMI (2021, 2022), IJCV (2020), NeurIPS (2020), AAAI (2020), VRST (2020), Eurographics (2019), Pacific Graphics (2018), CAVW (2018), ICCV Workshop PeopleCap (2017), IEEE VR (2017)
Outstanding Reviewer, CVPR 2020

Outstanding Reviewer, CVPR 2021

Outstanding Reviewer, ICCV 2021    ("top" reviewers in computer vision 2020-2021)
trojan Teaching Assistant, CSCI 576 Multimedia Systems Design, Fall 2021

Teaching Assistant, CSCI 677 Advanced Computer Vision , Fall 2019

Teaching Assistant, CSCI 621 Digital Geometry Processing, Spring 2018

Grader, EE 559 Mathematical Pattern Recognition, Spring 2015

Latest update: March 31, 2022.
Wonderful template from Jon Barron.