PeopleofSuperintelligence

Researcher

Dan Xu

Also known as 徐旦

Dan Xu is a computer vision researcher whose papers on depth estimation, scene parsing and SLAM help machines understand 2D and 3D scenes. He earned a PhD in computer science from the University of Trento in 2018 under Nicu Sebe and held a postdoctoral post in the Visual Geometry Group at the University of Oxford in 2019. His papers include a spotlight on continuous CRFs for monocular depth at CVPR 2017, PAD-Net at CVPR 2018, and GS-SLAM at CVPR 2024, which first used 3D Gaussian representation in a SLAM system. He won the Best Scientific Paper Award at ICPR in 2016 and was a Best Paper Award nominee at ACM Multimedia in 2018. He is an Associate Professor in the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology.

Timeline

  1. 2016

    Best Scientific Paper at ICPR

    He receives the Intel Best Scientific Paper Award at ICPR in 2016.

  2. 2017

    Continuous CRFs for depth estimation

    In 2017, he and coauthors Elisa Ricci, Wanli Ouyang, Xiaogang Wang and Nicu Sebe present a deep model for single-image depth estimation that fuses multi-scale CNN outputs with continuous conditional random fields. The paper is accepted as a spotlight at CVPR 2017.

  3. 2018

    PhD at the University of Trento

    He receives his PhD in computer science from the University of Trento in 2018, supervised by Nicu Sebe. He is also a visiting PhD student in the MMLab at the Chinese University of Hong Kong under Xiaogang Wang.

  4. 2018

    PAD-Net for scene understanding

    At CVPR 2018, he, Wanli Ouyang, Xiaogang Wang and Nicu Sebe present PAD-Net, a network that predicts intermediate auxiliary tasks and distils them for joint depth estimation and scene parsing. He is also a Best Paper Award nominee at ACM Multimedia in 2018.

  5. 2019

    Postdoc at Oxford's VGG

    In 2019, he is a postdoctoral researcher in the Visual Geometry Group (VGG) in the Department of Engineering Science at the University of Oxford, working with Andrea Vedaldi and Andrew Zisserman.

  6. By 2021

    Assistant Professor at HKUST

    He joins the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology as an Assistant Professor. In October 2021, he gives a department seminar on 2D and 3D scene understanding with deep learning.

  7. 2024

    GS-SLAM with 3D Gaussians

    In 2024, he coauthors GS-SLAM at CVPR with Chi Yan, Delin Qu, Bin Zhao, Zhigang Wang, Dong Wang and Xuelong Li. The system first uses 3D Gaussian representation in a SLAM system, with a real-time differentiable splatting rendering pipeline that speeds up map optimization and RGB-D rendering.

  8. As of October 2026

    Associate Professor at HKUST

    He is an Associate Professor in the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology, with research interests in computer vision, machine learning and multimedia. Five of his PhD students complete their degrees in 2025 and 2026, and he serves as Senior Programme Committee member or Area Chair at conferences including AAAI, ACM Multimedia and WACV.

Career

  1. Since 2021Hong Kong University of Science and TechnologyAssistant Professor
  2. 2019University of OxfordPostdoctoral researcher
  3. 2018Chinese University of Hong KongVisiting PhD student

Education

  1. 2018University of TrentoPhD in computer science

From the biography.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Dan Xu. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  2. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Hong Kong University of Science and Technology. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  3. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Hong Kong University of Science and Technology. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  4. Google has the highest combined h-index among AI organizationsIncludes Hong Kong University of Science and Technology. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Dan Xu yet. Send us a free-licensed photo.

  1. 牛津大学徐旦博士访问实验室并做报告 robotics.pkusz.edu.cn. Checked 21 October 2026.
  2. Dan XU - HKUST Department of Computer Science and Engineering cse.hkust.edu.hk. Checked 21 October 2026.
  3. Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation arxiv.org. Checked 21 October 2026.
  4. PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing openaccess.thecvf.com. Checked 21 October 2026.
  5. When 2D and 3D Scene Understanding Meets Deep Learning and Big Visual Data - HKUST CSE seminar cse.hkust.edu.hk. Checked 21 October 2026.
  6. GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting openaccess.thecvf.com. Checked 21 October 2026.
  7. Faculty Profiles - XU Dan | The Hong Kong University of Science and Technology facultyprofiles.hkust.edu.hk. Checked 21 October 2026.