Shitong Luo 罗世通
Undergraduate
Peking University
Shitong Luo is a final year undergraduate student majoring in Data Science at Peking University. He is now a research intern at Wangxuan Institue of Computer Technology and 
Mila - Quebec AI Institute. He is interested in geometric data processing and geometric deep learning.
Email: luost AT pku.edu.cn
GitHub
Selected Publications (view all)
Denoising Gradient Fields for Point Clouds
Submitted to CVPR 2021
Learning gradient fields for effective and robust point cloud denoising and beyond.
Diffusion Probabilistic Models for 3D Point Cloud Generation
Submitted to CVPR 2021
Inspired by the diffusion process in non-equilibrium thermodynamics; Markov chain; Achieving state-of-the-art performance in generation and auto-encoding.
Learning Neural Generative Dynamics for Molecular Conformation Generation
Minkai Xu* Shitong Luo* Yoshua Bengio Jian Peng Jian Tang (* indicates equal contribution)
International Conference on Learning Representations (ICLR) 2021
Flow-based model for molecular conformation generation; Using EBM for fine-tuning; Generating inter-atomic distances to preserve roto-translational invariance; High diversity and fidelity.
Differentiable Manifold Reconstruction for Point Cloud Denoising
ACM International Conference on Multimedia (ACM MM) 2020 Oral
Neural network architecture for point cloud denoising; Achieving state-of-the-art-performance; Surface-fitting based; Downsample-upsample scheme; Robust against high noise.