iiinova — where your digital self keeps evolving

Reposted by Jon Barron

Alexander Kustov @akoustov.bsky.social · 10/03/2026

I see many folks are pledging not to use AI in their writing. I pledge the opposite: I will use the latest LLMs, and for that matter any other available tool, to best improve my research or the way I communicate it. That way, if my name is on it, you can be sure it reflects my own best judgment.

11565

Reposted by Jon Barron

Zhenjun Zhao @ericzzj.bsky.social · 04/12/2025

Radiance Meshes for Volumetric Reconstruction Alexander Mai, Trevor Hedstrom, @grgkopanas.bsky.social, Janne Kontkanen, Falko Kuester, @jonbarron.bsky.social tl;dr: Delaunay tetrahedralization->constant density and linear color radian->radiance mesh->radiance field arxiv.org/abs/2512.04076

031

Reposted by Jon Barron

Paul Gavrikov @paulgavrikov.bsky.social · 08/09/2025

Is basic image understanding solved in today’s SOTA VLMs? Not quite. We present VisualOverload, a VQA benchmark testing simple vision skills (like counting & OCR) in dense scenes. Even the best model (o3) only scores 19.8% on our hardest split.

2175

Reposted by Jon Barron

Hà Phan @hpdailyrant.bsky.social · 16/07/2025

Here’s what I’ve been working on for the past year. This is SkyTour, a 3D exterior tour utilizing Gaussian Splat. The UX is in the modeling of the “flight path.” I led the prototyping team that built the first POC. I was the sole designer and researcher on the project, one of the 1st inventors.

5665

Reposted by Jon Barron

Matthias Niessner @niessner.bsky.social · 27/05/2025

🚀🚀🚀Announcing our $13M funding round to build the next generation of AI: 𝐒𝐩𝐚𝐭𝐢𝐚𝐥 𝐅𝐨𝐮𝐧𝐝𝐚𝐭𝐢𝐨𝐧 𝐌𝐨𝐝𝐞𝐥𝐬 that can generate entire 3D environments anchored in space & time. 🚀🚀🚀 Interested? Join our world-class team: 🌍 spaitial.ai youtu.be/FiGX82RUz8U

youtu.be

SpAItial AI: Building Spatial Foundation Models

YouTube video by SpAItial AI

5539

Jon Barron @jonbarron.bsky.social · 28/04/2025

Here's a recording of my 3DV keynote from a couple weeks ago. If you're already familiar with my research, I recommend skipping to ~22 minutes in where I get to the fun stuff (whether or not 3D has been bitter-lesson'ed by video generation models) www.youtube.com/watch?v=hFlF...

youtube.com

Radiance Fields and the Future of Generative Media

YouTube video by Jon Barron

25912

Jon Barron @jonbarron.bsky.social · 08/04/2025

A thread of thoughts on radiance fields, from my keynote at 3DV: Radiance fields have had 3 distinct generations. First was NeRF: just posenc and a tiny MLP. This was slow to train but worked really well, and it was unusually compressed --- The NeRF was smaller than the images.

29321

Jon Barron @jonbarron.bsky.social · 19/03/2025

Here's Bolt3D: fast feed-forward 3D generation from one or many input images. Diffusion means that generated scenes contain lots of interesting structure in unobserved regions. ~6 seconds to generate, renders in real time. Project page: szymanowiczs.github.io/bolt3d Arxiv: arxiv.org/abs/2503.14445

1356

Jon Barron @jonbarron.bsky.social · 19/03/2025

I made this handy cheat sheet for the jargon that 6DOF math maps to for cameras and vehicles. Worth learning if you, like me, are worried about embarrassing yourself in front of a cinematographer or naval admiral.

0335

Jon Barron @jonbarron.bsky.social · 24/02/2025

Can someone point me to a video of renderings of some 3DGS-like algorithm *as it is being optimized*? I want to see all those little Gaussians wobbling around.

240

Jon Barron @jonbarron.bsky.social · 23/02/2025

Next week is the one year anniversary of this paper showing that videos generated from Sora are nearly 3D-consistent. I'm surprised we never saw any follow-up papers in this line evaluating other videos models this way, it would be helpful to track these metrics over time. arxiv.org/abs/2402.17403

3432

Jon Barron @jonbarron.bsky.social · 22/02/2025

Veo 2 now has a public price point: $0.50 per second. Very important number to keep in mind when considering the future of generative and non-generative media. Taken from cloud.google.com/vertex-ai/ge...

0110

Jon Barron @jonbarron.bsky.social · 18/02/2025

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:

210924

Jon Barron @jonbarron.bsky.social · 12/02/2025

My pitch for an "LLM-native" alternative to citation count/h-index etc: 1) Train an LLM on a new paper and record the average loss during training. 2) Evaluate the retrained LLM on benchmarks. Your Google Scholar records avg_train_loss * benchmark_delta, and you go write your next paper.

140

Reposted by Jon Barron

Sander Dieleman @sedielem.bsky.social · 10/02/2025

Great interview with @jascha.sohldickstein.com about diffusion models! This is the first in a series: similar interviews with Yang Song and yours truly will follow soon. (One of these is not like the others -- both of them basically invented the field, and I occasionally write a blog post 🥲)

youtube.com

History of Diffusion - Jascha Sohl-Dickstein

YouTube video by Bain Capital Ventures

04311

Reposted by Jon Barron

nealwadhwa.bsky.social @nealwadhwa.bsky.social · 09/02/2025

With the CVPR 2025 rebuttal deadline over, it’s the perfect time to submit a demo application for CVPR 2025. Demos can be any application of computer vision in the real world and are a great way to show off your work to other #computervision enthusiasts. Submit here docs.google.com/forms/d/e/1F...

docs.google.com

CVPR 2025 Demo Submission

Submission page for the Demo Track at CVPR 2025. Read the call for demos on the CVPR Website.

0135

Jon Barron @jonbarron.bsky.social · 07/02/2025

fun test for image and video generation systems: add "the camera is upside down" to the prompt (especially for shots of people) and then vertically mirror the output. Even the best models struggle, with upside-down teeth and blinks, and gravity tugging everything up. Here's Veo 2.

2121

Jon Barron @jonbarron.bsky.social · 25/01/2025

I fed the "spinning dancer" illusion (a silhouette of a spinning figure that can be seen as rotating clockwise or counter-clockwise, left) into Runway Gen-3 (right). It resolved the ambiguity by having the dancer face the camera and oscillate, which is kinda clever.

3220

Jon Barron @jonbarron.bsky.social · 10/01/2025

`A 1960s NASA scientist with a white button down shirt and black heavy rimmed glasses, with a giant thick alien umbilical cord coming out of the back of his body. The cord is holding him up in space, and he is levitating around his office. Wide angle, full body shot.` #Veo2

190

Jon Barron @jonbarron.bsky.social · 10/01/2025

"A fun children's educational program where Mr. See-thru teaches kids about how the gastrointestinal system works using his semitransparent abdomen." #Veo2 I'm surprised by how well Veo 2 understands human anatomy, and amused by the things that it doesn't yet understand.

1120

Reposted by Jon Barron

Ethan Mollick @emollick.bsky.social · 03/01/2025

I have been having fun turning the Mario Brothers into a 1940s industrial film using Veo 2.

627842

Jon Barron @jonbarron.bsky.social · 03/01/2025

In case it's helpful to others writing papers or doing comparisons, I'm hosting raw mp4s for the #Veo2 results I've been posting, with no Bluesky-induced compression: drive.google.com/drive/folder.... Here's `A kraken emerging from the ocean at the beach on coney island`, which I forgot to post.

1121

Jon Barron @jonbarron.bsky.social · 02/01/2025

`An advertisement for a shoe made of broccoli romanesco, rotating on a turntable` #Veo2

250

Reposted by Jon Barron

Johan Edstedt @parskatt.bsky.social · 02/01/2025

Going to put "Towards" in my title, you can't stop me.

2171

Jon Barron @jonbarron.bsky.social · 01/01/2025

Happy Hanukkah! "A man using an upside-down Hanukkah menorah as a jetpack, blasting off" #Veo2

2151

Jon Barron @jonbarron.bsky.social · 01/01/2025

"A colorized 1950s TV commercial. Left: a dad struggling to pick up a heavy box. Right: that dad wearing a full-body mechanical exoskeleton, lifting the box with ease." #Veo2

0100

Jon Barron @jonbarron.bsky.social · 31/12/2024

"A giraffe riding four skateboards, one for each foot" #Veo2

3140

Jon Barron @jonbarron.bsky.social · 30/12/2024

Happy Hanukkah! "A row of industrial robot arms grabbing latkes from a conveyor belt and dunking them into a row of bowls of sour cream" #Veo2

1111

Jon Barron @jonbarron.bsky.social · 27/12/2024

It's been a month and this website still isn't nearly as good as the other one.

3140

Jon Barron @jonbarron.bsky.social · 25/12/2024

"Tilt-shift footage of Woodstock 1969" #Veo2

010

Jon Barron @jonbarron.bsky.social · 25/12/2024

"A banana in a bodybuilding competition, striking different poses with its floppy little peel-arms" #Veo2

0110

Jon Barron @jonbarron.bsky.social · 24/12/2024

"A person putting on a hat that is a giant strawberry, and then the person grabs a chunk of it off their head and eats it" #Veo2

080

Jon Barron @jonbarron.bsky.social · 24/12/2024

"A woman using a hairdryer, except the hairdryer is shooting a fountain of rainbow sprinkles onto her head and hair" #Veo2

060

Jon Barron @jonbarron.bsky.social · 24/12/2024

"A giant millipede who just escaped from the zoo and is wreaking havoc in downtown manhattan" #Veo2

130

Jon Barron @jonbarron.bsky.social · 23/12/2024

"Aerial footage of someone flying a wingsuit through Times Square in Manhattan, in 1974" #Veo2

0140

Jon Barron @jonbarron.bsky.social · 23/12/2024

"A canopy bed galloping across the savanna" #Veo2

0194

Jon Barron @jonbarron.bsky.social · 23/12/2024

I tried to render what an o3 prompt for ARC-AGI might look like from an LLM's point of view. A hard way to ingest a grid of integers!

260

Jon Barron @jonbarron.bsky.social · 21/12/2024

okay I've had it with people calling a collection of 3D Gaussians "a splat". It's ungrammatical! The proper term for a group of Gaussians is "a carl", named of course in honor of Carl Friedrich Gauss. A murder of crows, a pod of whales, a carl of Gaussians. Got it? Sheesh.

1341

Jon Barron @jonbarron.bsky.social · 20/12/2024

Every time someone calls a collection of 3D Gaussians "a splat" a radiance field angel loses its wings.

1140

Jon Barron @jonbarron.bsky.social · 20/12/2024

Image: "A pig sitting in front of a slot machine" Motion: "The arm of the slot machine moves down, causing gold coins to come bursting out of the bottom of the slot machine, showering the pig with coins" #Veo2

370

Jon Barron @jonbarron.bsky.social · 20/12/2024

Has anyone figured out what genesis-world.readthedocs.io is or does yet? I still don't get it.

genesis-world.readthedocs.io

Genesis — Genesis 0.2.0 documentation

260

Jon Barron @jonbarron.bsky.social · 19/12/2024

`A tracking shot following a futuristic personal submarine blasting through an cybernetic underwater utopia of glass domes and tubes and sparkling lights at high speed.` #Veo2

1100

Jon Barron @jonbarron.bsky.social · 19/12/2024

`An elderly man in a suit bursting out of an egg` #Veo2

070

Jon Barron @jonbarron.bsky.social · 18/12/2024

Is there an LLM service that improves the HTML of a website to make it render better across different resolutions and platforms? I want an LLM agent that tidies some HTML, renders a page into virtual mobile and desktop images, looks at the renderings, and repeats.

310

Jon Barron @jonbarron.bsky.social · 18/12/2024

Spotted this in the wild. I know it kinda doesn't make sense, but CVPR 2025 submissions can't be publicly stated as such on arxiv or on your personal website. If you wrote "in submission to CVPR 2025" somewhere on the open internet, you should delete it ASAP.

2216

Jon Barron @jonbarron.bsky.social · 16/12/2024

If you ask Grok 2 to generate an image of yourself, it appears to look at your Twitter profile picture, summarize it into a text description, and then generate an image from that text. It will then tell you the image was just a guess based on generalities about your tweets.

130

Jon Barron @jonbarron.bsky.social · 14/12/2024

The popular Max/MSP UI for procedural audio generation is an interesting glimpse into one potential future for image/video generation interfaces like ComfyUI. Having a time-axis is gonna make things a lot more complicated. cycling74.com/products/max

1130