Aria Gen 2 applications are open. Our next generation hardware unlocks new possibilities.

Today, we’re excited to announce that applications are now open for researchers to receive Aria Gen 2, targeting a broad rollout of Aria Gen 2 devices to qualified applicants in Q2 2026.

Bridging the Gap: Introducing Boxer for Open-World 2D-to-3D Lifting

We are excited to announce Boxer: a new, lightweight and modular model designed to lift open-world 2D bounding boxes into high-precision metric 3D oriented bounding boxes (3DBBs), enabling more detailed annotation of objects in 3D space.
April 22, 2026

Sonata: Advancing Self-Supervised Learning for 3D Point Representations

June 4, 2025

Reading Recognition in the Wild: A dataset for understanding human behaviors during reading from egocentric sensor suite

June 4, 2025

Inside Aria Gen 2: Explore the Cutting-Edge Tech Behind the Device

Today, we’re excited to share more about the technology inside Aria Gen 2. This includes an in-depth overview of the form factor, audio capabilities, battery life, upgraded cameras and sensors, on-device compute, and more.
June 4, 2025

Introducing Aria Gen 2: Unlocking New Research in Machine Perception, Contextual AI, Robotics, and More

Today, we're excited to announce the next step in the Project Aria journey: the introduction of Aria Gen 2 research glasses.
February 27, 2025

Introducing Nymeria, a dataset for improving human motion prediction for AR and VR devices

The Nymeria dataset provides egocentric human motion in the wild at an unprecedented scale, capturing a broad spectrum of people engaging in everyday activities across varied locations.
December 20, 2024

Project Aria Research Kit: Case Studies + a Call for Applications

Today, we’re sharing some case studies of exciting work undertaken with Project Aria and inviting members of the research community to apply for the Aria Research Kit (ARK).
November 13, 2024

Introducing the Digital Twin Catalog from Reality Labs Research

Reality Labs Research is releasing the Digital Twin Catalog (DTC), which we believe is the world’s largest and highest quality 3D object model dataset for 3D reconstruction research.
September 30, 2024

Introducing the Aria Training and Evaluation toolkit (ATEK)

Today, we’re introducing ATEK, an e2e framework for training and evaluating deep learning models on Aria data, for both 3D egocentric-specific and general machine perception tasks.
September 26, 2024