PeopleofSuperintelligence

Researcher

Pedro Sander

Also known as Pedro V. Sander, 辛達德

Pedro Sander is a computer graphics researcher whose work on colorization networks and neural radiance fields brings deep learning into rendering. Raised mostly in Brasília, he earned a PhD at Harvard University in 2003, worked at ATI Research, and moved to Hong Kong in 2006. At the Hong Kong University of Science and Technology, he coauthored Deep Exemplar-based Colorization for SIGGRAPH 2018 and Deblur-NeRF at CVPR 2022, and he was general co-chair of the I3D conference in 2014. In 2026, he coauthored RetimeGS for CVPR and Hybrid Gaussian Wang Tiles for SIGGRAPH. He is a professor of computer science and engineering at HKUST.

Badges

Timeline

  1. 1994–2003

    Stony Brook and Harvard degrees

    After an early life mostly in Brasília, Brazil, he studies computer science at Stony Brook University from 1994 and earns his bachelor's degree in 1998. He completes a master's degree at Harvard University in 1999 and a PhD in 2003, with fellowships from Harvard's Division of Engineering and Applied Sciences and from Microsoft Research.

  2. 2003–2006

    Senior member at ATI Research

    From 2003 to 2006, he is a senior member of the Application Research Group of ATI Research in Marlborough, Massachusetts. There he researches real-time rendering and general-purpose computation on current and upcoming graphics hardware.

  3. 2006

    Joining HKUST in Hong Kong

    In 2006, he moves to Hong Kong to join the Faculty of Computer Science and Engineering at the Hong Kong University of Science and Technology (HKUST). He specializes in computer graphics, with emphasis on geometry processing, real-time rendering, and graphics hardware.

  4. 2011–2017

    Chairing graphics conferences

    He chairs the Courses program for ACM SIGGRAPH Asia 2011. He is general co-chair of the I3D conference in 2014 and its papers co-chair in 2015, and papers co-chair of EGSR in 2017.

  5. 2018–2019

    Deep exemplar-based colorization

    In 2018, he coauthors Deep Exemplar-based Colorization with Mingming He, Dongdong Chen, Jing Liao and Lu Yuan, a convolutional network that colors a grayscale image from a reference color image, for SIGGRAPH 2018. In 2019, a video version coauthored with Bo Zhang, Mingming He, Jing Liao, Lu Yuan and others adds a recurrent framework for temporal consistency.

  6. 2022

    Deblur-NeRF at CVPR 2022

    In 2022, he coauthors Deblur-NeRF at CVPR with Li Ma, Xiaoyu Li, Jing Liao, Qi Zhang, Xuan Wang and Jue Wang. The method recovers a sharp neural radiance field from blurry input views by simulating the blurring process.

  7. 2024–2026

    NeRF and Gaussian splatting work

    In 2024, he coauthors SpecNeRF, a CVPR paper that adds a learnable Gaussian directional encoding to neural radiance fields to model specular reflections. In 2026, he coauthors RetimeGS, a CVPR method for rendering dynamic scenes at arbitrary timestamps, and is corresponding author of Hybrid Gaussian Wang Tiles for SIGGRAPH 2026.

  8. As of October 2026

    Professor at HKUST

    He is a Professor in the Department of Computer Science and Engineering at HKUST, in the Vision and Graphics area, and has been on the faculty there since 2006.

Career

  1. Since 2006Hong Kong University of Science and TechnologyProfessor
  2. 2003–2006ATI TechnologiesSenior Member

Education

  1. 2003Harvard UniversityPhD
  2. 1999Harvard UniversityMaster's degree
  3. 1998Stony Brook UniversityBachelor's degree

From the biography.

  1. 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.
  2. 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.
  3. 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.
  4. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Hong Kong University of Science and Technology. 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.

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 Pedro Sander yet. Send us a free-licensed photo.

  1. Pedro SANDER | HKUST CSE cse.ust.hk. Checked 22 October 2026.
  2. Pedro V. Sander – ACM SIGGRAPH HISTORY ARCHIVES history.siggraph.org. Checked 22 October 2026.
  3. Prof. Pedro SANDER Expands on His Passion for Computer Graphics | HKUST School of Engineering seng.hkust.edu.hk. Checked 22 October 2026.
  4. Presenter | SIGGRAPH Asia 2022 Daegu sa2022.siggraph.org. Checked 22 October 2026.
  5. [1807.06587] Deep Exemplar-based Colorization arxiv.org. Checked 22 October 2026.
  6. [1906.09909] Deep Exemplar-based Video Colorization arxiv.org. Checked 22 October 2026.
  7. CVPR 2022 Open Access Repository: Deblur-NeRF: Neural Radiance Fields From Blurry Images openaccess.thecvf.com. Checked 22 October 2026.
  8. CVPR 2024 Open Access Repository: SpecNeRF: Gaussian Directional Encoding for Specular Reflections openaccess.thecvf.com. Checked 22 October 2026.
  9. CVPR 2026 Open Access Repository: RetimeGS: Continuous-Time Reconstruction of 4D Gaussian Splatting openaccess.thecvf.com. Checked 22 October 2026.
  10. Hybrid Gaussian Wang Tiles for Class-aware Authoring and Rendering - The Hong Kong University of Science and Technology Research Portal researchportal.hkust.edu.hk. Checked 22 October 2026.
  11. Faculty | HKUST CSE cse.ust.hk. Checked 22 October 2026.