Siyuan Huang

Seattle I am a third year Ph.D. student in the Department of Statistics at University of California, Los Angeles. I am currently doing computer vision research at the Center for Vision, Cognition, Learning, and Autonomy (VCLA) and am advised by Professor Song-Chun Zhu. Before coming to UCLA, I graduated from Tsinghua University with a Bachelors in Department of Automation.


My research interests lie on computer vision, machine learning and robotics. I currently focus on the problem of 3D scene understanding which contains 3D scene parsing, reconstruction and synthesis. I would like to develop tools to help machines learn 3D representations, percept 3D world, and interact with 3D environment from images or videos.
E-Mail / CV / Google Scholar
News
  • NEW   I am co-organizing the CVPR 2019 workshop: 3D Scene Understanding for Vision, Graphics and Robotics.
  • 09/2018 One Paper accepted by NeurIPS 2018. Code is released.
  • 07/2018 One Paper accepted by ECCV 2018.
  • 06/2018 One Paper accepted by IJCV 2018.
  • 02/2018 One Paper accepted by CVPR 2018.
  • 04/2017: One paper accepted by ICCV 2017.
  • 09/2016: Started my Ph.D. at UCLA



Publications
NeurIPS 2018 Cooperative Holisctic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation
Siyuan Huang, Siyuan Qi, Yinxue Xiao, Yixin Zhu, Ying Nian Wu, Song-Chun Zhu
Neural Information Processing Systems (NeurIPS) 2018
Paper / Supplementary / Poster / Video / Code / Project
Propose an end-to-end model that simultaneously solves tasks of 3D object detection, 3D layout estimation and camera pose estimation in real-time given only a single RGB image


ECCV 2018 Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image
Siyuan Huang, Siyuan Qi, Yixin Zhu, Yinxue Xiao, Yuanlu Xu, Song-Chun Zhu
European Conference on Computer Vision (ECCV) 2018
Paper / Supplementary / Project / Code / Poster / Bibtex
Propose a computational framework to parse and reconstruct the 3D configuration of an indoor scene from a single RGB image in an analysis-by-synthesis fasion using a stochastic grammar model.



IJCV 		Configurable 3D Scene Synthesis and 2D Image Rendering with Per-Pixel Ground Truth using Stochastic Grammars
Chenfanfu Jiang *, Siyuan Qi *, Yixin Zhu *, Siyuan Huang *, Jenny Lin, Xingwen Guo, Lap-Fai Yu, Demetri Terzopoulos, Song-Chun Zhu
* Equal contributions
Internatianal Journal of Computer Vision (IJCV) 2018
Paper / Demo
Employ physics-based rendering to synthesize photorealistic RGB images while automatically synthesizing detailed,per-pixel ground truth data, including visible surface depth and normal, object identity and material information, as well as illumination.


CVPR 2018 Human-centric Indoor Scene Synthesis using Stochastic Grammar
Siyuan Qi, Yixin Zhu , Siyuan Huang, Chenfanfu Jiang , Song-Chun Zhu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018
Paper / Project / Code / Bibtex
Present a human-centric method to sample and synthesize 3D room layouts and 2D images thereof, for the purpose of obtaining large-scale 2D/3D image data with the perfect per-pixel ground truth.


ICCV 2017 Predicting Human Activities Using Stochastic Grammar
Siyuan Qi, Siyuan Huang, Ping Wei, Song-Chun Zhu
IEEE International Conference on Computer Vision (ICCV) 2017
Paper / Bibtex / Code
Use a stochastic grammar model to capture the compositional structure of events, integrating human actions, objects, and their affordances for modeling the rich context between human and environment.



arXiv 2015 Nonlinear Local Metric Learning for Person Re-identification
Siyuan Huang, Jiwen Lu, Jie Zhou, Anil K. Jain
arXiv 2015
arXiv Paper
Utilize the merits of both local metric learning and deep neural network to exploit the complex nonlinear transformations in the feature space of person re-identification data.

icip 2015 Building Change Detection Based on 3D reconstruction
Baohua Chen, Lei Deng, Yueqi Duan, Siyuan Huang, Jie Zhou
IEEE International Conference on Image Processing (ICIP) 2015
Paper / Bibtex
Propose a change detection framework based on RGB-D map generated by 3D reconstruction which can overcome the large illumination changes .