PeopleofSuperintelligence

Researcher

Gang Zeng

Gang Zeng is a computer vision and graphics researcher whose work spans facade modeling, scene parsing and 3D scene generation. He earned a B.S. at Peking University in 2001 and a Ph.D. in computer science and technology at HKUST in 2006, then worked as a postdoctoral fellow at ETH Zurich from 2006 to 2008. His 2007 facade paper combined shape grammars with image analysis; his scene-parsing result placed fourth at ILSVRC 2016, and he received awards at MPR in 2011, CCCV in 2017 and ICPR in 2018. He coauthored SceneAssistant in 2026, a visual-feedback agent for open-vocabulary 3D scene generation. As of October 2026, he is a researcher and doctoral supervisor in Peking University's School of Intelligence Science and Technology.

Works
133
Citations
7,868
h-index
38
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2001

    A mathematics degree

    He earns a B.S. degree from Peking University's School of Mathematical Sciences in 2001.

  2. 2006–2008

    An ETH Zurich postdoc

    He earns a Ph.D. in computer science and technology from the Hong Kong University of Science and Technology in 2006. From 2006 to 2008, he works as a postdoctoral research fellow in the BIWI Computer Vision Laboratory at ETH Zurich. In late 2008, Peking University selects him as a "Young Excellent Talent".

  3. 2007

    Image-based facade modeling

    In 2007, he coauthors *Image-based procedural modeling of facades*, which derives 3D building models from facade images by combining shape grammars with image analysis.

  4. 2011

    An MPR poster award

    He receives the Best Poster Award at the 2011 MPR International Workshop.

  5. 2016

    Fourth in ILSVRC scene parsing

    At ILSVRC 2016, his scene-parsing result places fourth. The SegModel entry lists Gang Zeng among the authors and says its models are fine-tuned from ResNet-152.

  6. 2017–2018

    CCCV and ICPR paper awards

    He receives CCCV's Best Paper Award in 2017. In 2018, he shares ICPR's Best Scientific Paper Award with Jiyuan Zhang and Hongbin Zha for *Scalable Monocular SLAM by Fusing and Connecting Line Segments with Inverse Depth Filter*.

  7. 2026

    SceneAssistant for open-vocabulary scenes

    In 2026, he coauthors SceneAssistant, a visual-feedback agent that uses a vision-language model to generate open-vocabulary 3D scenes and refine them through rendered feedback.

  8. As of October 2026

    Researcher at Peking University

    As of October 2026, he is a researcher and doctoral supervisor in Peking University's School of Intelligence Science and Technology. His areas include computer vision and graphics, 3D scene modeling, image- or interaction-based modeling and rendering, and automated image segmentation.

Career

  1. Since 2010Peking UniversityResearcher and doctoral supervisor
  2. 2006–2008ETH ZurichPostdoctoral Research Fellow

Education

  1. 2006Hong Kong University of Science and TechnologyPhD in computer science and engineering
  2. 2001Peking UniversityB.S.

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Gang Zeng. 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. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Peking University. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  3. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Peking University. 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. Companies supply the most prior-work hires at 7 of the 9 frontier AI labsIncludes Peking University. Our estimates of the organizations where 550 people worked directly before joining 9 frontier AI labs across 620 career transitions, comparing the main feeder organizations per lab.

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 Gang Zeng yet. Send us a free-licensed photo.

  1. Gang Zeng — Peking University Institute for Artificial Intelligence ai.pku.edu.cn. Checked 22 October 2026.
  2. Contributor — SIGGRAPH Asia 2025 Conference Schedule sa2025.conference-schedule.org. Checked 22 October 2026.
  3. Image-based procedural modeling of facades — Arizona Board of Regents experts.azregents.edu. Checked 22 October 2026.
  4. ILSVRC 2016 results — ImageNet image-net.org. Checked 22 October 2026.
  5. Best Scientific Paper Awards — ICPR 2018 iapr.org. Checked 22 October 2026.
  6. SceneAssistant: A Visual Feedback Agent for Open-Vocabulary 3D Scene Generation — arXiv arxiv.org. Checked 22 October 2026.