📢📢📢 We have released data, models and training code for Omni3D. If you are into large-scale, generalizable solutions in the intersection of recognition and 3D, Omni3D is your testbed ✅ 234k images ✅ 3 million objects ✅ 97 object types sourced from existing 3D datasets!

I made an intelligent image captioner using Detic and #chatGPT. Demo: huggingface.co/spaces/taesiri…

Announcing data2vec 2.0, a new general self-supervised algorithm built by Meta AI for speech, vision & text that can train models 16x faster than the most popular existing algorithm for images while achieving the same accuracy. Read more & get the open source code ⬇️

Introducing RT-1, a robotic model that can execute over 700 instructions in the real world at 97% success rate! Generalizes to new tasks✅ Robust to new environments and objects✅ Fast inference for real time control✅ Can absorb multi-robot data✅ Powers SayCan✅ 🧵👇

What do Vision Transformers Learn? A Visual Exploration abs: arxiv.org/abs/2212.06727 github: github.com/hamidkazemi22/…

Proud to give this sneak peak of the teams hard work :) thanks for the highlight Dmytro Mishkin 🇺🇦

📢 I will be presenting EgoLifter with Julian Straub tomorrow at ECCV! Time: Tue Oct 1st, 10:30 - 12:30 Location: Poster #176 In case you missed it, the code has been released here: github.com/facebookresear… (please give a star 😁)

Interested in 3D object detection and egocentric vision? We open sourced a small yet challenging dataset called Aria Everyday Objects (AEO). We use it as one of the tasks for benchmarking a new class of Egocentric 3D Foundation Models we are working on: arxiv.org/abs/2406.10224

Project Aria is at European Conference on Computer Vision #ECCV2026 until 6pm today! Come try our streaming demo and learn about our new open datasets, models, and tools at the Meta booth.

Third Egocentric Research Tutorial with Project Aria Recording available on Youtube! youtu.be/m6oFLfYUpoM?si… Has my EFM3D talk at about 1:57h into the recording!

Our team is proud to announce Aria Gen 2, the most advanced wearable sensor platform in the world. Following Orion's announcement last year, and Aria 1st-Gen in 2020, Aria Gen 2 will help us solve challenges on the path to full AR glasses and ContextualAI 😎

The first generation of Aria glasses have made a big impact in the research community, can't wait to see all the new possibilities these will unlock meta.com/blog/project-a…

Introducing Aria Gen 2, next generation glasses that we hope will enable researchers from industry and academia to unlock new work in machine perception, contextual AI, robotics and more. Aria Gen 2 details + sign up for availability updates ➡️ go.fb.me/8rku3b

Checkout our 3D point cloud SSL approach! 3x improvement on linear probing performance for semantic segmentation!

The next OpenSUN3D workshop takes place at #ICCV2025 -- we are excited to announce a fantastic line-up of speakers: 👩‍💼 Mackenzie Weygandt Mathis, PhD Saining Xie Julian Straub @angelxchang Iro Armeni ⏱️Date/time: Oct. 19, 1:30pm--6pm (1st day, afternoon) 🏡Details: opensun3d.github.io

Hmmm Fladenbrot und Humus - selbst gemacht :-)