Jia Deng

About

Jia Deng is a Professor of Computer Science at Princeton University, where he directs the Princeton Vision & Learning Lab. His research focuses on computer vision and machine learning, contributing to advancements in these fields through his academic work. Throughout his career, he has received numerous awards and honors, including the Best Student Paper Award at 3DV 2021, the Best Paper Award at ECCV 2020, the ONR Young Investigator Award in 2020, and the NSF CAREER Award in 2020. His recognition also includes the PAMI Longuet-Higgins Prize in 2019, an Alfred P. Sloan Research Fellowship in 2018, and multiple Google Faculty Research Awards, among others. His work has significantly impacted the development of computer vision and machine learning, establishing him as a leading researcher in these areas.

Research topics

• Computer Science
• Artificial Intelligence
• Mathematics
• Geography
• Physics
• Algorithm
• Computer vision
• Cartography

Selected publications

• RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

  Lecture notes in computer science · 2020 · 2310 citations

  Senior authorCorresponding
  DOI

• RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching

  2021 International Conference on 3D Vision (3DV) · 2021 · 440 citations

  Senior authorCorresponding

  We introduce RAFT-Stereo, a new deep architecture for rectified stereo based on the optical flow network RAFT [35]. We introduce multi-level convolutional GRUs, which more efficiently propagate information across the image. A modified version of RAFT-Stereo can perform accurate real-time inference. RAFT-stereo ranks first on the Middlebury leaderboard, outperforming the next best method on 1px error by 29% and outperforms all published work on the ETH3D two-view stereo benchmark. Code is availab…

  PublisherDOI

• Towards fairer datasets

  2020 · 222 citations

  Computer vision technology is being used by many but remains representative of only a few. People have reported misbehavior of computer vision models, including offensive prediction results and lower performance for underrepresented groups. Current computer vision models are typically developed using datasets consisting of manually annotated images or videos; the data and label distributions in these datasets are critical to the models' behavior. In this paper, we examine ImageNet, a large-scale…

  DOI

• Infinite Photorealistic Worlds Using Procedural Generation

  2023-06-01 · 56 citations

  articleSenior author

  We introduce Infinigen, a procedural generator of photorealistic 3D scenes of the natural world. Infinigen is entirely procedural: every asset, from shape to texture, is generated from scratch via randomized mathematical rules, using no external source and allowing infinite variation and composition. Infinigen offers broad coverage of objects and scenes in the natural world including plants, animals, terrains, and natural phenomena such as fire, cloud, rain, and snow. Infinigen can be used to ge…

  PublisherDOI

• SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow

  Lecture notes in computer science · 2024-09-28 · 43 citations

  book-chapterSenior author
  PublisherDOI

Recent grants

• RI: Small: Inverse Rendering by Co-Evolutionary Learning

  NSF · $467k · 2016–2018

• BIGDATA: F: Collaborative Research: From Visual Data to Visual Understanding

  NSF · $355k · 2016–2018

• BIGDATA: F: Collaborative Research: From Visual Data to Visual Understanding

  NSF · $199k · 2018–2020

Frequent coauthors

• Li Fei-Fei

  29 shared

• Jonathan Krause

  Google (United Kingdom)

  16 shared

• Kaiyu Yang

  14 shared

• Olga Russakovsky

  13 shared

• Alexander C. Berg

  11 shared

• Weifeng Chen

  11 shared

• Alejandro Newell

  10 shared

• Zachary Teed

  10 shared

Labs

• Vision & Learning LabPI

  Vision and Learning Lab at Princeton University

Awards & honors

• Best Student Paper Award, 3DV 2021
• Best Paper Award, ECCV 2020
• ONR Young Investigator Award, 2020
• NSF CAREER Award, 2020
• PAMI Longuet-Higgins Prize, 2019

Similar researchers at Princeton University

• Nathaniel Dawh-96
• Sanjeev Arorah-84
• Carlos Brodyh-59