I'm Xiangru Huang (黄相如). I'm received my PhD in Computer Science Department of University of Texas at Austin under professor Qixing Huang . My research focuses on Geometry Processing, 3D Vision and Efficient Optimization algorithms. I received my Bachelor's Degree from Shanghai JiaoTong University, ACM Honored Class.
I'm working as a post-doc with Justin Solomon at MIT. For more details, please check my CV.
Email: xiangruhuang816 at gmail dot com
Github: xiangruhuang
GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Models
[arXiv]
Haitao Yang, Xiangru Huang, Bo Sun, Chandrajit Bajaj, Qixing Huang
April 20th, 2023
LiDAR-Based 3D Object Detection via Hybrid 2D Semantic Scene Generation
[arXiv]
Haitao Yang, Zaiwei Zhang, Xiangru Huang, Min Bai, Chen Song, Bo Sun, Li Erran Li, Qixing Huang
April 04th, 2023
Surface Representation in Real Scenes (in submission, to appear on arXiv)
Haoxi Ran, Xiangru Huang, Vitor Guizilini, Yue Wang
Hybrid Geometric Primitives for Point Clouds (in submission, to appear on arXiv)
Xiangru Huang*, Marianne Arrirola*, Yue Wang, Vitor Guizilini, Rares Ambrus, and Justin Solomon. (Equal Contribution)
Representation Learning for Object Detection from Unlabeled Point Cloud Sequences
[code]
[paper]
Xiangru Huang, Yue Wang, Vitor Guizilini, Rares Ambrus, Adrien Gaidon and Justin Solomon.
Conference on Robotic Learning (CoRL) 2022.
ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators.
[paper]
[supp]
[code]
Bo Sun, Xiangru Huang, Zaiwei Zhang, Junfeng Jiang, Qixing Huang, and Chandrajit Bajaj.
International Conference on Computer Vision (ICCV) 2021.
Dense Human Correspondence via Learning Transformation Synchronization on Graphs.
[pdf]
[poster]
[code]
Xiangru Huang, Haitao Yang, Etienne Vouga and Qixing Huang.
2020 Conference on Neural Information Processing Systems. (Neurips 2020).
Uncertainty Quantification for Multi-scan Registration.
[pdf]
[poster]
[code]
Xiangru Huang*, Zhenxiao Liang* and Qixing Huang. (* equally contributed)
ACM Transactions on Graphics, 39(4), Proceedings of ACM SIGGRAPH 2020.
Learning Transformation Synchronization.
[pdf]
[poster]
[code]
Xiangru Huang, Zhenxiao Liang, Xiaowei Zhou, Yao Xie, Leonidas Guibas, and Qixing Huang.
Computer Vision and Pattern Recognition (CVPR) 2019.
Joint Map and Symmetry Synchronization.
[pdf]
Yifan Sun*, Zhenxiao Liang*, Xiangru Huang* and Qixing Huang. (* equally contributed)
European Conference on Computer Vision (ECCV) 2018.
Translation Synchronization via Truncated Least Squares. (spotlight presentation)
[pdf]
[poster]
[slides]
Xiangru Huang*, Zhenxiao Liang*, Chandrajit Bajaj and Qixing Huang. (* equally contributed)
In Advances in Neural Information Processing Systems (NIPS), 2017
PPDSparse: A Parallel Primal and Dual Sparse Method to Extreme Classification.
[pdf]
Ian E.H. Yen, Xiangru Huang, Wei Dai, Pradeep Ravikumar, Inderjit S. Dhillon and Eric P. Xing.
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2017.
Greedy Direction Method of Multiplier for MAP Inference of Large Output Domain.
[pdf]
[code]
Xiangru Huang, Ian E.H. Yen, Ruohan Zhang, Qixing Huang, Pradeep Ravikumar and Inderjit S. Dhillon.
Artificial Intelligence and Statistics (AISTATS), 2017.
Dual Decomposed Learning with Factorwise Oracle for Structural SVM of Large Output Domain. [pdf]
[code]
[slides]
[poster]
Ian E.H. Yen, Xiangru Huang, Kai Zhong, Ruohan Zhang, Pradeep Ravikumar and Inderjit S. Dhillon.
In Advances in Neural Information Processing Systems (NIPS), 2016.
PD-Sparse: A Primal and Dual Sparse Approach to Extreme Multiclass and Multilabel Classification.
[pdf]
[code]
Ian E.H. Yen*, Xiangru Huang*, Kai Zhong, Pradeep Ravikumar and Inderjit S. Dhillon. (* equally contributed)
In International Conference on Machine Learning (ICML), 2016.
Trial and error in influential social networks.
[pdf]
Xiaohui Bei, Ning Chen, Liyu Dou, Xiangru Huang, Ruixin Qiang. (ordered alphabetically by last name)
In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2013.
MAP-Sublinear
A efficient and accurate solver for MAP inference problems. Compared to state-of-the-art solvers (e.g. TRW-S, AD3, MPLP, etc.), our solvers is orders of magnitude faster without downgrading accuracy.
Fast Structual SVM
A efficient structual SVM solver designed to deal with 1) large factor domain and 2) large number of factors. (for details please check this NIPS 2016 paper)
PD-Sparse
Efficient solver for multiclass and multilabel classification problems. Designed to solve problems with millions of classes/labels with single core. We're working on a distributed version of this. (for details please check this ICML 2016 paper)
CS311 Discrete Math , Fall 2014
CS345 Programming Languages, Spring 2015
CS371p Object-Oriented Programming, Fall 2015
CS324E Elements of Graphics, Spring 2016
CS324E Elements of Graphics, Fall 2016
CS395T Numerical Optimization for Graphics and AI, Fall 2017
CS395T Numerical Optimization for Graphics and AI, Fall 2018