Are you confused and frustrated by the diverse presentations of diffusion models in papers? Check out this wonderful blog by Sander Dieleman that presents an overview of the many perspectives on diffusion. sander.ai/2023/07/20/per…

My intuition is, finally all 3D models should be trained by videos, and only videos. Endless videos on the internet (the problem is license though).

Grounding Image Matching in 3D with MASt3R Vincent Leroy, Yohann Cabon, Jerome Revaud tl;dr: DUSt3R+new head with dense local features output+InfoNCE loss; in 3D space; high-resolution (coarse-to-fine matching+fast reciprocal matching) arxiv.org/pdf/2406.09756

Happening in 20 minutes!!

Big crowd around Jonathon Luiten presenting SplaTAM! Too bad Nikhil Keetha and Jay Karhade couldn't make it. Also one of the godfathers of SLAM in the crowd (can you spot him?)

The wait is over 📢 MAST3R is out! DUSt3R+ dense local feature maps & metric depth - 1st in #MapFreeReloc leaderboard, can handle 1000s of images 😀 !! Blog: shorturl.at/9JTH2 Code: github.com/naver/mast3r Paper: arxiv.org/abs/2406.09756

How to Map 🗺️ It Anywhere? mapitanywhere.github.io The trick is to flip the script from using principally limited self-collected datasets to using readily available worldwide maps. Head over to our website to generate your own data or see our FPV Mapper in action! 🧵👇 1/n

🚀 Ready to take 3D reconstruction to the next level? Whether you're working on NeRF or 3DGS, our new method, GLOMAP, is here to impress! 🌟 It's faster and more accurate than COLMAP on several datasets. 🌐 Website: lpanaf.github.io/eccv24_glomap/ Marc Pollefeys, Linfei Pan, J. Schönberger

This is very cool! TLDR; DUSt3R predicting pointmaps in global coordinate frame (eliminating need for BA). A very neat way and implicitly SLAMy. hengyiwang.github.io/projects/spann…

Really exciting collaboration led by JennySeidenschwarz, online 3D point tracking and NVS from unposed videos!

Places are composed of things. Recognizing & retrieving these things instead of the whole image enables 🧭viewpoint invariance 🖼️semantic interpretability 🔮open-set recognition 🧵on our #ECCV2024 paper: Revisit Anything: Visual Place Recognition via Image Segment Retrieval 👇

I'll be presenting UpFusion as a poster at #ECCV2024 European Conference on Computer Vision #ECCV2026! 🗓️Date: Oct 1 | 4:30pm - 6:30pm (CEST) 📍Poster: 213 💻Project Page: upfusion3d.github.io Do consider visiting our poster to learn more about our take on pose-free sparse-view reconstruction!

we’re hiring World Labs seeking insanely great engineers + designers to work alongside our world-class research team to imagine and build entirely new apps and experiences made possible at the rapidly expanding frontier of generative AI + 3D computer vision + graphics

Excited to share MonST3R! -- a simple way to estimate geometry from unposed video of dynamic scene We achieve competitive results on several downstreams (video depth, camera pose) and believe this is a promising step toward feed-forward 4D reconstruction monst3r-project.github.io

Humans can learn to reason in an "unfamiliar" world, like new games. How far are LLMs from this? Check out our recent work @NeurIPS2024 D&B Track: "LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation". Page: jaraxxus-me.github.io/LogiCity/

We’ve been busy building an AI system to generate 3D worlds from a single image. Check out some early results on our site, where you can interact with our scenes directly in the browser! worldlabs.ai/blog 1/n

Very excited to share with you what our team World Labs has been up to! No matter how one theorizes the idea, it's hard to use words to describe the experience of interacting with 3D scenes generated by a photo or a sentence. Hope you enjoy this blog! 🤩❤️‍🔥

Today we're sharing our first research update World Labs -- a generative model of 3D worlds! I'm super proud of what the team has achieved so far, and can't wait to see what comes next. Lifting GenAI to 3D will change the way we make media, from movies to games and more!