Justin Johnson
World Labs co-founder; first author of the perceptual-losses, CLEVR and DenseCap papers in computer vision
- Co-founder, World Labs12
Justin Johnson is one of the founders of World Labs, the spatial intelligence company started with Fei-Fei Li, Ben Mildenhall and Christoph Lassner, and Johnson's GitHub profile lists World Labs as Johnson's organization. Johnson is first author of papers on perceptual losses for real-time style transfer, the CLEVR visual reasoning dataset and DenseCap dense captioning, and a co-author of Mesh R-CNN and PyTorch3D.1234567
Career
Research
Johnson's early papers, written with Fei-Fei Li and others, include DenseCap (2015) on dense image captioning with Andrej Karpathy, the perceptual-losses paper (2016) on real-time style transfer and super-resolution, and the CLEVR dataset (2016) for diagnosing visual reasoning. Johnson's GitHub account hosts the reference code for the perceptual-losses paper in the fast-neural-style repository, alongside the densecap repository.53482
Later work moved toward 3D understanding: Johnson co-authored Mesh R-CNN (2019) with Georgia Gkioxari and Jitendra Malik, which predicts 3D meshes from images, and the 2020 paper describing the PyTorch3D library.67
Work
Perceptual Losses for Real-Time Style Transfer and Super-Resolution (external site: arxiv.org)Published research
First author, with Alexandre Alahi and Fei-Fei Li, of the 2016 paper that trains feed-forward networks for image transformation tasks such as style transfer and super-resolution using perceptual loss functions.38
CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning (external site: arxiv.org)Open data
First author of the 2016 paper introducing CLEVR, a diagnostic dataset for testing compositional language and elementary visual reasoning.4
Accelerating 3D Deep Learning with PyTorch3D (external site: arxiv.org)Open-source code
Co-author of the 2020 paper describing PyTorch3D, a library for 3D deep learning.7
Career timeline
Nov 2015
Posted DenseCap, on fully convolutional localization networks for dense captioning, as first author.5
Mar 2016
Posted the perceptual-losses paper on real-time style transfer and super-resolution as first author.3
Dec 2016
Posted the CLEVR visual reasoning dataset paper as first author.4
Jun 2019
Co-authored Mesh R-CNN with Georgia Gkioxari and Jitendra Malik.6
Jul 2020
Co-authored the paper describing the PyTorch3D library for 3D deep learning.7
Related people
More sourced profiles at the same organization, in the same field, or from the same school.
- Ben MildenhallAlso at World Labs
- Aditya RameshImage, video, and 3D generation
- Christoph LassnerAlso at World Labs
- Alex NicholImage, video, and 3D generation
- Fei-Fei LiAlso at World Labs
- Alexei A. EfrosComputer vision
- Amir HertzImage, video, and 3D generation
- Angjoo KanazawaComputer vision
- Bichen WuComputer vision
- Bilawal SidhuImage, video, and 3D generation
- David ForsythComputer vision
- David LuebkeImage, video, and 3D generation
Is this you?
Profiles cover public professional work only, and every line cites a source. If something is out of date, missing or wrong, send a correction with a link to an official page and we will update it. Suggest a correction
Add this badge to your website or GitHub profile README. It links back to this page. It is not an endorsement or a rating.
Markdown (for a README)
[](https://unitedstatesofamericasuperintelligence.com/people/justin-johnson/)
HTML
<a href="https://unitedstatesofamericasuperintelligence.com/people/justin-johnson/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/profile.svg" alt="Justin Johnson — Profile on USASI" height="20"></a>
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.