Siyi Chen

Home

Research

Understanding 3D Object Articulation in Internet Videos (CVPR 2022)

Shengyi Qian, Linyi Jin, Chris Rockwell, *Siyi Chen, David Fouhey*

Website

Combined Understanding of 3D Plane Articulation and Partial Human Pose Estimation

Advisor: David Fouhey

Mentor: Shengyi Qian

sure

  1. Independently predict 3D partial human poses as SMPL meshes in pytorch3d following Rockwell’s methods. And use PointRend to obtain 2D human masks.

  2. Independently predict 2D plane masks as well as 3D articulation information.

  3. Use a differential render in pytorch3d similar to the NMR in PHOSA for back-propagation, to build a similar system optimizing the position and size of the person considering 3d space relationship and interaction for each single image.

GitHub Poster

Convex Presentations of Translation Surfaces

Student Group: Andrew Keisling, Brendan Nell, Kaiwen Lu, Siyi Chen

Advisors: Chaya Norton, Paul Apisa

Mentors: Christopher Zhang, Sayantan Khan

origami

  1. We (a group of students really green to topology) have designed and implemented beta versions of enumerating origamis in H(2).
  2. We have utilized SageMath to implement the convexity test presented in this paper by Lelievre and Weiss.

Abstract GitLab Report Poster