Education

I’m a second-year direct doctorate student in ETH Zurich. I completed my bachelor degree of computer science at Turing Class, Peking University, in June 2023.

Research

I’m now conducting research at Computer Vision and Learning Group (VLG) with Prof. Dr. Siyu Tang. I’m also interning at Google now.

Previous experience

During my undergraduate studies, I worked in Visual Computing And Learning (VCL) lab under the supervision of Prof. Baoquan Chen, Prof. Libin Liu, and Prof. Mengyu Chu. I had a wonderful summer internship in 2022 with Dr. Lingjie Liu and Dr.Marc Habermann at MPI for Informatics (Visual Computing and AI Department led by Prof. Dr. Christian Theobalt ).

Research Interests

For my research interests, I am interested in the intersection of computer vision and computer graphics. In particular, my current researches focus on neural scene representations, neural rendering, human performance capture and 3D reconstruction.

Publications

• Physics-Informed Learning of Characteristic Trajectories for Smoke Reconstruction
  Yiming Wang, Siyu Tang, Mengyu Chu
  SIGGRAPH 2024
  [Project Page] [Paper] [Code]

• NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction
  Yiming Wang*, Qin Han*, Marc Habermann, Kostas Daniilidis, Christian Theobalt, Lingjie Liu
  ICCV 2023
  [Project Page] [Paper] [Code]

• Neural Novel Actor: Learning a Generalized Animatable Neural Representation for Human Actors
  Qingzhe Gao*, Yiming Wang*, Libin Liu, Lingjie Liu, Christian Theobalt, Baoquan Chen
  TVCG 2023
  [Project Page] [Paper]

• Edit-History Vis: An Interactive Visual Exploration and Analysis on Wikipedia Edit History
  Yuhan Guo, Qin Han, Yuke Lou, Yiming Wang, Can Liu, Xiaoru Yuan
  PacificVis 2023

Selected Awards

• John Hopcroft Scholarship (2021)
• CASC first grade scholarship (2020)

Skills

Languages: Python, Pytorch, C/C++, CUDA, OpenGL, JavaScript

Projects:

• NVIDIA OPTIX (An application framework for achieving optimal ray tracing performance on the GPU, and my practice project)

• 3D human pose estimation in crowded scenes