PeopleofSuperintelligence

Researcher

Angela Dai

Angela Dai is a computer scientist whose work teaches machines to understand, model and generate real-world 3D environments. After a Princeton degree in 2013, she earned a Stanford PhD in 2018 under Pat Hanrahan, co-created the ScanNet dataset of 1513 indoor RGB-D scenes in 2017, and became a professor at the Technical University of Munich in 2020. In 2022, she won the Eurographics Young Researcher Award and an ERC Starting Grant, and in 2024 she received the ECVA Young Researcher Award and the German Pattern Recognition Award. MeshGPT, coauthored in 2023, generates triangle meshes with a decoder-only transformer. She is an Associate Professor at TUM, where she leads the 3D AI Lab.

Timeline

  1. 2013–2018

    Princeton and a Stanford PhD

    She earns a BSE in computer science at Princeton in 2013. At Stanford, she completes a PhD in computer science in 2018 under the advisor Pat Hanrahan.

  2. 2017

    ScanNet and BundleFusion

    In 2017, she is first author of ScanNet, an RGB-D video dataset of 1513 indoor scenes with 2.5M views, annotated with 3D camera poses, surface reconstructions and semantic segmentations. BundleFusion, a real-time globally consistent 3D reconstruction method she coauthors, appears in ACM Transactions on Graphics in 2017.

  3. 2019–2020

    SIGGRAPH honor and a TUM professorship

    She receives an Honorable Mention for the ACM SIGGRAPH Outstanding Doctoral Dissertation Award in 2019 and holds a ZDB Junior Research Group Award from 2019. In 2020, she becomes a professor at the Technical University of Munich, where she leads the 3D AI Lab.

  4. 2022

    Eurographics award and ERC grant

    Eurographics gives her its 2022 Young Researcher Award for her work on 3D scene reconstruction and semantic scene understanding, citing BundleFusion and the ScanNet datasets. The European Research Council awards her a 2022 Starting Grant for the project "Spatial 3D Semantic Understanding for Perception in the Wild".

  5. November 2023

    MeshGPT for triangle meshes

    She coauthors MeshGPT with Matthias Nießner and colleagues in November 2023. The model generates triangle meshes as sequences of triangles with a decoder-only transformer, and it improves shape coverage by 9% and FID scores by 30 points over earlier mesh generation methods.

  6. 2024

    ECVA and DAGM awards

    The European Computer Vision Association gives her its Young Researcher Award in 2024 for her work on 3D scene reconstruction and semantic scene understanding. DAGM also grants her the German Pattern Recognition Award in 2024.

  7. 2025–2026

    Program Chair for CVPR 2026

    She serves as Program Chair for Eurographics 2025 and for CVPR 2026.

  8. As of October 2026

    Associate Professor at TUM

    She is an Associate Professor at the Technical University of Munich, where she leads the 3D AI Lab. Her research aims to enable machines to understand, model and generate real-world 3D environments.

Career

  1. Since 2020Technical University of MunichAssociate Professor

Education

  1. 2018Stanford UniversityPhD in computer science

From the biography.

  1. Language models reach 33% of 2020s entrants, and company shares run from 8% in pattern recognition to 91% in AI infrastructureIncludes Angela Dai. We estimate how research topics in AI changed across seven entry decades (6,853 people from the 1960s to the 2020s) and how 60 major topics split between companies (8% to 91%) and universities (10% to 93%).
  2. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Technical University of Munich. 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.
  3. Google has the highest combined h-index among AI organizationsIncludes Technical University of Munich. 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.
  4. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Technical University of Munich. 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.

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 Angela Dai yet. Send us a free-licensed photo.

  1. Prof. Dr. Angela Dai professoren.tum.de. Checked 21 October 2026.
  2. Young Researcher Award 2022 – Angela Dai eg.org. Checked 21 October 2026.
  3. ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes arxiv.org. Checked 21 October 2026.
  4. Prof. Angela Dai receives ERC Starting Grant cit.tum.de. Checked 21 October 2026.
  5. MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers arxiv.org. Checked 21 October 2026.
  6. Angela Dai Receives ECVA Young Researcher Award 2024 mcml.ai. Checked 21 October 2026.
  7. Angela Dai Receives German Pattern Recognition Award 2024 mcml.ai. Checked 21 October 2026.
  8. Team - 3D AI Lab 3dunderstanding.org. Checked 21 October 2026.