Hao Su

Assistant Professor at UC San Diego

Bldg EBU3B #4114
Dept. of Computer Science and Engineering
UC San Diego, La Jolla, USA

haosu AT eng.ucsd.edu / bio / CV / google scholar / publication

Follow @HaoSuLabUCSD on Twitter


  • [Oct 11, 2021] ManiSkill accepted by NeurIPS (dataset track).
  • [Oct 1, 2021] We have two papers accepted by NeurIPS (visual RL, 3D physics data understanding).
  • [July 29, 2021] The National Science Foundation (NSF) announced a $20 million investment over five years for The Institute for Learning-enabled Optimization at Scale (TILOS). SU Lab is part of TILOS.
  • [July 22, 2021] Four papers accepted at ICCV 2021 (two orals).
  • [May 29, 2021] Welcome to our ICCV workshop of SEAI: Simulation Technology for Embodied AI and Structural and Compositional Learning on 3D Data.
  • [Mar 1, 2021] Two paper accepted at CVPR 2021 (oral).
  • [Jan 28, 2021] One paper in collaboration with Prof. Rajesh Gupta's group accepted at AISTATS (oral).
  • [Jan 13, 2021] One paper (transcription factor binding) accepted at Nature Machine Intelligence (Jan 2021 volume).
  • [Jan 12, 2021] Two papers (model-based policy learning (spotlight), 3D learning (poster)) accepted at ICLR 2021.
  • [Dec 9, 2020] I am giving invited talks at UPenn, UToronto, Nvidia, and 3DGV on Compositional Generalizability.
  • [Nov 6, 2020] Check out the latest technical report on a proposal of benchmarking the learning of embodied AI (robotics)!
  • [Sept 25, 2020] Three papers (Algorithm learning, Generalizable reinforcement learning) accepted at NeurIPS 2020.
  • [July 2, 2020] Two papers (3D Reconstruction) accepted at ECCV 2020.
  • [June 30, 2020] One paper (Learning for SLAM) accepted at IROS 2020.
  • [May 31, 2020] One paper (ML theory) accepted at ICML 2020.
  • [Mar 13, 2020] Four papers (3D learning, simulator) accepted at CVPR 2020, two orals and two posters.
  • [Dec 20, 2019] Two papers (3D learning, imitation learning) accepted at ICLR 2020.
  • [Oct 26, 2019] The 2019 version of 3D Deep Learning Tutorial is online now!
  • [Oct 22, 2019] I am serving on the Area Chair for CVPR 2020, ECCV 2020, the Senior Program Committee of AAAI 2020 this year.
  • [Sep 7, 2019] One paper (grasping by 3D learning) accepted at Conference on Robotics Learning (CoRL) 2019 (27.6% acceptance rate).
  • [Sep 3, 2019] One paper (model-based reinforcement learning) accepted at NeurIPS 2019.
  • [Sep 1, 2019] Zhan Ling, Minghua Liu, and Xiaoshuai Zhang are joining SU Lab as new Ph.D. students!
  • [Sep 1, 2019] Tongzhou Mu is promoted to Ph.D. after two years of hard work as a master student!
  • [Aug 6, 2019] I have received the best doctorate thesis award honorable mention from ACM SIGGRAPH.
  • [July 28, 2019] One paper accepted at SIGGRAPH Asia 2019.
  • [July 22, 2019] One paper accepted at ICCV 2019 as oral.
  • [Mar 25, 2019] One paper accepted at SIGGRAPH 2019.
  • [Feb 25, 2019] Five papers from my students have been accepted at CVPR 2019.
  • [Sep 4, 2018] I have one paper accepted at NIPS 2018.
  • [Sep 4, 2018] I have one paper accepted at SIGGRAPH Asia 2018.
  • [July 10, 2018] I am thrilled that ShapeNet has received the dataset award of SGP (Symposium on Geometry Processing) 2018!
  • [Apr 15, 2018] I am proud to have Jiayuan Gu, Zhiao Huang, Zhiwei Jia, Ronald Yu, and Rui Zhu join my group as Ph.D. students starting from this fall!
  • [Feb 19, 2018] I have 4 papers accepted at CVPR 2018.
  • [July 7, 2017] A set of tutorial slides for 3D deep learning is uploaded. See the Talk and Course section of this webpage.
  • [Jun 6, 2017] I will join the Computer Science and Engineering Department of UC San Diego as an assistant professor starting from July 1, 2017.
  • [May 5, 2017] I am serving the program chair of 3DV 2017.
  • [Mar 31, 2017] I am organizing the IEEE Workshop on Learning to See from 3D Data in conjunction with ICCV 2017, Venice, Italy.
  • [Mar 31, 2017] I have one paper accepted at SIGGRAPH 2017.
  • [Feb 27, 2017] I have 5 papers (2 first author orals, 1 spotlight, 2 posters) accepted at CVPR 2017.
  • [Feb 24, 2017] I am giving an invited talk at UC San Diego in April.
  • [Feb 10, 2017] I am giving an invited talk at Cornell University in April.
  • [Jan 17, 2017] I am organzing a tutorial on 3D Deep Learning at CVPR 2017, Hawaii, USA.
  • [Dec 15, 2016] Posted the slides of my recent talks on 3D representation learning and synthesis for learning. They summarize the majority of my efforts in the past 3 years.
  • [Nov 24, 2016] I am giving talks at MIT (Brain and Cognitive Sciences Department and CSAIL), on 3D object reconstruction and abstraction by deep learning.
  • I will give a talk at Adobe and Facebook on understanding geometries from sensor data.
  • I am invited to give a talk at NIPS workshop on 3D Deep Learning and 3DV workshop on Understanding 3D and Visuo-Motor Learning. See you there!
  • I have published 1 paper at NIPS, 3 papers at SIGGRAPH Asia, 1 paper at ECCV (spotlight), 2 papers at CVPR (1 spotlight) in 2016, and 1 paper at 3DV (oral) in 2016.
  • I am serving the Publication Chair for International Conference on 3DVision (3DV-16), Stanford, USA. Welcome to join us and visit Stanford!
  • I am organizing the IEEE Workshop on Augmented Reality for Visual Artificial Intelligence (VARVAI), affiliated with ECCV 2016, Amsterdam, The Netherlands
  • I am serving the program committee for the First Workshop on Virtual Reality meets Physical Reality: Modelling and Simulating Virtual Humans and Environments, affiliated with SIGGRAPH Asia 2016, Macau, China
  • I organized the Large-Scale 3D Shape Retrieval Challenge, a subtrack of SHREC2016 Challenge affiliated with EuroGraphics 2016, Lisbon, Portugal
  • To visit Europe for two weeks in early November of 2015 and give talks on Joint Analysis for 2D Images and 3D shapes at several institutes, including Max Planck Institute (Germany), Ecole Polytechnique (France), Ecole Normale SupA(C)rieure (France), Tel Aviv University (Israel) and The Hebrew University of Jerusalem (Israel).
  • Talk on Joint Analysis for 2D Images and 3D shapes at UC Berkeley, Oct 16, 2015.
  • I have two oral papers accepted by ICCV 2015 (2% acceptance rate for oral presentation).
  • I have one paper accepted by SIGGRAPH Asia 2015.
  • I am organizing the IEEE Workshop on 3D Representation and Recognition (3dRR-15) in conjunction with ICCV 2015, Santiago, Chile.
  • I am organizing the IEEE Workshop on 3D from a Single Image (3DSI-15) in conjunction with CVPR 2015, Boston, USA.
  • Gave three talks during my visit in China this summer, at Tsinghua University, Beihang University, and Shandong University, Aug, 2015.
  • Talk on Joint Analysis for 2D Images and 3D shapes at UCLA, March, 2015.
  • Talk on Depth Estimation from a Single Image via Shape Collection at UC Berkeley, Aug, 2014.

Research Interest

Theories and technologies to build autonomous systems that can Actively and Continuously Learn in the Physical World.

Computer Vision and Computer Graphics

  • Crowd-sourcing for Large-scale Dataset Construction
  • 3D Object/Scene Understanding

Machine Learning and Generic AI

  • Reinforcement Learning
  • Imitation Learning
  • Concepts and Causal Relationships


  • Object Manipulation
  • Realistic Physical Simulator for Robot Training and Benchmarking

Community Services


  • CVPR: Area Chair 2019, 2020, 2021
  • ECCV: Area Chair 2020
  • ICCV: Area Chair 2019
  • 3DV: Program Chair 2017


  • TOG: Associate Editor 2021-2024


  • IROS: Associate Editor 2021
  • ICRA: Associate Editor 2021, 2022

Artificial Intelligence

  • AAAI: Senior Program Committee 2020
  • Southern California Machine Learning Seminar: Co-Chair 2021


Fall Quarter (CSE152, entry-level): Introduction to Computer Vision

The first computer vision course that UCSD CSE students take.

Winter Quarter (CSE291, advanced): Machine Learning meets Geometry

revamped version of the previous 3D ML course with more references to recent progress of deep learning method for geometry.

Spring Quarter (CSE291, advanced): Machine Learning for Robotics

Topics on how to apply machine learning for solving robotics problems.

Course IV: Deep Learning Lab for Computer Vision (CSE291-J, graduate level)

A lab course that trains students to do computer vision projects using deep learning.

Tutorial: A 90 min Tutorial on 3D Deep Learning

A tutorial of 3D Deep Learning (updated on April 3, 2020). Keynote   PPTX   PDF   Video


Reference to all papers in plain text format Bibtex for all papers
Research keywords
Year published

Academic calendar

Click here