Log inSign up
Jon Barron
3,065 posts
user avatar
Jon Barron
@jon_barron
Principal research scientist at Google DeepMind. Synthesized views are my own.
SF Bay Area
jonbarron.info
Joined May 2010
1,390
Following
34.2K
Followers
  • Pinned
    user avatar
    Jon Barron
    @jon_barron
    Apr 28, 2025
    Here's my 3DV talk, in chapters: 1) Intro / NeRF boilerplate. 2) Recent reconstruction work. 3) Recent generative work. 4) Radiance fields as a field. 5) Why generative video has bitter-lessoned 3D. 6) Why generative video hasn't bitter-lessoned 3D. 5 & 6 are my favorites.
    123K
  • user avatar
    Jon Barron
    @jon_barron
    Jun 12, 2024
    Love it.
    8.7M
  • user avatar
    Jon Barron
    @jon_barron
    Jun 12, 2024
    Replying to @Eli_Schwartz
    I think the point was to get caught, it's basically a performance art piece on the part of the submitter.
    161K
  • user avatar
    Jon Barron
    @jon_barron
    Dec 2, 2024
    World Labs just dropped their first results/demos!
    00:00
    240K
  • user avatar
    Jon Barron
    @jon_barron
    Feb 12, 2025
    MIT trained... an eyeball? What?
    00:00
    331K
  • user avatar
    Jon Barron
    @jon_barron
    Feb 18, 2025
    I just pushed a new paper to arXiv. I realized that a lot of my previous work on robust losses and nerf-y things was dancing around something simpler: a slight tweak to the classic Box-Cox power transform that makes it much more useful and stable. It's this f(x, λ) here:
    00:00
    236K
  • user avatar
    Jon Barron
    @jon_barron
    Mar 3, 2022
    Very glad I can finally talk about our newly-minted #CVPR2022 paper. We extended mip-NeRF to handle unbounded "360" scenes, and it got us ~photorealistic renderings and beautiful depth maps. Explainer video: youtube.com/watch?v=zBSH-k… and paper: arxiv.org/abs/2111.12077
    00:00
  • user avatar
    Jon Barron
    @jon_barron
    Oct 27, 2023
    David MacKay's "Dasher" project made a big impact on me when I first learned about it in university. It's a way to write text by steering a cursor/joystick through what is basically an n-gram language. Someone should revive this idea and do it with an LLM. inference.org.uk/dasher/
    00:00
    168K
  • user avatar
    Jon Barron
    @jon_barron
    Jun 12, 2024
    Replying to @jon_barron
    Photographer Disqualified From AI Image Contest After Winning With Real Photo
    From petapixel.com
    174K
  • user avatar
    Jon Barron
    @jon_barron
    Jan 17, 2023
    Three years ago today, the project that eventually became NeRF started working (positional encoding was the missing piece that got us from "hmm" to "wow"). Here's a snippet of that email thread between Matt Tancik, @_pratul_, @BenMildenhall, and me. Happy birthday NeRF!
    279K
  • user avatar
    Jon Barron
    @jon_barron
    Jan 14, 2022
    18 months ago: "Training a NeRF takes 5 hours..." 2 months ago: "Training a NeRF takes 5 minutes!" Yesterday: "Training a NeRF takes 5 seconds!!??" Not only are NeRFs getting faster, the rate at which they get faster is increasing. This is crazy.
    user avatar
    AK
    @_akhaliq
    Jan 14, 2022
    Instant Neural Graphics Primitives with a Multiresolution Hash Encoding paper: nvlabs.github.io/instant-ngp/as… project page: nvlabs.github.io/instant-ngp/ github: github.com/NVlabs/instant…
    00:00
  • user avatar
    Jon Barron
    @jon_barron
    Sep 16, 2024
    New hobby: pushing 90s video game recordings through Gen-3's Video2Video model. Here's Super Mario 3 as felt.
    00:00
    146K
  • user avatar
    Jon Barron
    @jon_barron
    Jun 19, 2020
    people.eecs.berkeley.edu/~bmild/fourfeat We figured out why the "positional encoding" used in NeRF works so well! NTK theory says that using an MLP with a Fourier basis yields a composed kernel that is good at interpolating (as per basic signal processing). Excited to see what people do with this
  • user avatar
    Jon Barron
    @jon_barron
    Jul 24, 2020
    I got really into a bunch of 1980s-era papers about histogram thresholding, and wrote a weird paper. I sent it to ECCV assuming the reviewer response would be "why are you writing a direct response to two 40 year old papers" but they loved it, so hey.

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms of Service|Privacy Policy|Cookie Policy|Accessibility|Ads info|© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up