Aria Gen 2 Case Study: Envision - Spatial Audio Navigation and AI Research Meta Open Source 2025-02-27 | Explore the possibilities with Aria Gen 2 in our new case study with Envision and LightHouse SF.In collaboration with Lighthouse SF, Envision is exploring the integration of its Ally AI assistant and spatial audio using Aria Gen 2 glasses to improve navigation for individuals who are blind and have low vision.The team leverages the on-device SLAM capabilities of Aria Gen 2, along with spatial audio features via onboard speakers to give a user spatialized audio cues to guide them to products they need in a grocery store. This work is still in an exploratory phase, but exemplifies how partners can leverage the new capabilities of Aria Gen 2 glasses for prototyping AI experiences.Read the blog post to learn more about Aria Gen 2: meta.com/blog/project-aria-gen-2-next-generation-egocentric-research-glasses-reality-labs-ai-roboticsLearn more about Envision: letsenvision.comLearn more about LightHouse SF: lighthouse-sf.org Learn more about Ally AI: ally.me
3D Digital Twin Workshop CVPR 2025: Building Models of Reality for Mixed Reality and Contextual AI Meta Open Source 2025-09-19 | Dr. Richard Newcombe, VP of Research Science At Reality Labs Meta explains the importance of digital twin asset creation in the context of spatial AI and next-gen human-centric compute platforms.
3D Digital Twin Workshop CVPR 2025: 4D Digital Twins from Videos in the Wild Meta Open Source 2025-09-19 | Dr. Qianqian Wang from UC Berkeley’s BAIR lab (Berkeley Artificial Intelligence Research) shares her work recreating 4D digital twins from monocular 2D videos.
3D Digital Twin Workshop CVPR 2025: Neural Relightable Assets Meta Open Source 2025-09-19 | Dr. Miloš Hašan presents his methods for creating neural relightable 3D assets.
3D Digital Twin Workshop CVPR 2025: Panel discussion Meta Open Source 2025-09-19 | Dr. Zhao Dong from Meta Reality Labs moderates a panel discussion about 3D Digital Twin at CVPR 2025 in Nashville, Tennessee with Prof. Andrea Vedaldi, Jerome Revaud, Dr. Xiaoshuai Zhang, Dr. Miloš Hašan, Dr. Shuang Zhao, Prof. Hao (Richard) Zhang, and Dr. Richard Newcome, VP at Meta Reality Labs.
3D Digital Twin Workshop CVPR 2025: Feed Forward Digital Twins Meta Open Source 2025-09-19 | Prof. Andrea Vedaldi from the University of Oxford presents methods of building foundational neural networks that solve problems in 3D scene and object reconstruction.
3D Digital Twin Workshop CVPR 2025: Meta’s Project Aria Meta Open Source 2025-09-19 | James Fort, Product Manager at Meta Reality labs positions Project Aria and Aria glasses in the context of 3D digital twins.
3D Digital Twin Workshop CVPR 2025: Capturing Reality End-to-End: Fast, Texture-Ready Digital Twins Meta Open Source 2025-09-19 | Dr. Xiaoshuai Zhang from Hillbot, discusses his recent work on practical high quality simulation and texture ready digital twin capture in the real world with nothing but a cellphone.
3D Digital Twin Workshop CVPR 2025: Opening Remarks and Welcome Meta Open Source 2025-09-19 | Dr. Zhao Dong from Meta Reality Labs introduces the motivations and groundwork for the workshop.
3D Digital Twin Workshop CVPR 2025: Learning Structured CAD Representations for 3D Digital Twins Meta Open Source 2025-09-19 | Prof. Richard (Hao) Zhang from Simon Fraser University discusses methods of generating digital twins for robotics using CAD tools.
3D Digital Twin Workshop CVPR 2025: Learning Generalizable Manipulation from Sim and Real Data Meta Open Source 2025-09-19 | Prof. Xiaolong Wang from UC San Diego discusses robot training methods, including the use of real world data from humans to train robot policies.
3D Digital Twin Workshop CVPR 2025: Physics-Based Inverse Rendering Meta Open Source 2025-09-19 | Dr. Shuang Zhao, Associate Professor of computer science at UC Irvine presents his work on the problem of inverse rendering, where scene parameters from one or more images can be used to infer one or multiple scene parameters (shape, reflectance, and lighting).
How Meta Built a Greener Data Center Using AI-Engineered Concrete Meta Open Source 2025-07-16 | Get a look inside Meta’s Rosemount Datacenter – built using low-carbon, high-performance concrete designed with AI. The sustainable concrete was designed using an open-source AI tool that Meta developed in collaboration with Amrize and the University of Illinois Urbana-Champaign. Why it matters: Concrete production accounts for 8% of all global CO2 emissions and is a major contributor to the embodied carbon emissions in data center construction. Meta’s aim is to scale the use of sustainable concrete in data centers and advance its goal of net zero emissions in 2030.Learn more here: engineering.fb.com/2025/07/16/data-center-engineering/ai-make-lower-carbon-faster-curing-concrete
EgoVis Workshop CVPR 2025: HoloAssist Challenge Meta Open Source 2025-06-24 | Taein Kwon, a postdoctoral research fellow at VGG at Oxford, presents challenge winners for the tasks action recognition and anticipation, mistake detection, and intervention type prediction using the HoloAssist dataset. HoloAssist is a large-scale egocentric human interaction dataset, where two people collaboratively complete physical manipulation tasks. Presenters include Constantin Patsch, Boyu Han, Wei-Jin Huang, Michele Mazzamuto, Maia Stiber, and Sean Andrist. HoloAssist website: holoassist.github.io/#HoloAssist
EgoVis Workshop CVPR 2025: Presentations on FIction, EgoPressure, Estimating Body and Hand Motion Meta Open Source 2025-06-24 | - FIction: 4D Future Interaction Prediction from Video arxiv.org/abs/2412.00932: 0:05- EgoPressure: A Dataset for Hand Pressure and Pose Estimation in Egocentric Vision arxiv.org/abs/2409.02224: 06:15- Estimating Body and Hand Motion in an Ego-sensed World arxiv.org/abs/2410.03665: 14:05 - Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory arxiv.org/abs/2411.16934: 19:30
EgoVis Workshop CVPR 2025: How good are foundation models at understanding video? Meta Open Source 2025-06-24 | Arsha Nagrani from Google Deepmind presents How Good are Foundation Models at understanding video? Arsha gives an overview on the state of foundation models, presents challenges, and proposes future directions for the field.
EgoVis Workshop CVPR 2025: Ego-4D and Ego-Exo4D Challenges Meta Open Source 2025-06-24 | Andrew Westbury presents the Ego4D and EgoExo4D 2025 Challenge winners- Julia Romero presents Keystep Recognition using Graph Neural Networks: 11:30 - Lorenzo Mur-Labadia presents O-MaMa Learning Object Mask Matching between Egocentric and Exocentric Views: 16:01 - Luigi Seminara presents Ego-Exo4D Procedure Understanding Challenge 2025: 20:32 - Md Mohaiminul Islam presents BIMBA: Selective-Scan Compression for Long Range Video Question Answering : 26:15- Yisen Feng presents OSGNet for Video Localization: 33:55
EgoVis Workshop CVPR 2025: Humanoid Policy Meta Open Source 2025-06-24 | Xiaolong Wang, Associate Professor at UC San Diego presents Humanoid Policy ~ Human Policy arxiv.org/abs/2503.13441
EgoVis Workshop CVPR 2025: Distinguished Paper Awards Meta Open Source 2025-06-24 | Prof. Dr. Dima Damen presents the 2023-2024 Distinguished Paper Awards for EgoVis.- AssemblyHands Towards Egocentric Activity Understanding via 3D Hand Pose Estimation arxiv.org/abs/2304.12301: 3:55 - Ego-4D Goal-Step: Toward Hierarchical Understanding of Procedural Activities neurips.cc/virtual/2023/poster/73705: 7:14 - EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exocentric View of Procedural Activities in Real World arxiv.org/abs/2403.16182: 11:20- HierVL: Learning Hierarchical Video-Language Embeddings arxiv.org/abs/2301.02311: 13:40 - It’s Just Another Day: Unique Video Captioning by Discriminative Prompting arxiv.org/abs/2410.11702: 15:12- LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuning arxiv.org/abs/2312.03849: 17:15- Video Recap: Recursive Captioning of Hour Long Videos arxiv.org/abs/2402.13250: 19:49
EgoVis Workshop CVPR 2025: Introducing Aria Gen 2 Meta Open Source 2025-06-24 | James Fort, Hyo-Jin Kim, and Cheng Peng present Project Aria, demo Aria Gen 2 glasses, and present the Reading in the Wild Dataset. Learn more about Project Aria: projectaria.comLearn more about Aria Gen 2: ai.meta.com/blog/aria-gen-2-research-glasses-under-the-hood-reality-labsLearn more about Reading in the Wild: projectaria.com/news/introducing-reading-recognition-in-the-wild
EgoVis Workshop CVPR 2025: Towards an Egocentric Multimodal Foundation Model Meta Open Source 2025-06-24 | Prof. Dr. Siyu Tang from ETH Zurich presents a keynote address titled Towards an Egocentric Multimodal Foundation Model at the Second Joint Egocentric Vision (EgoVis) Workshop - CVPR 2025. Dr. Tang discusses how multimodal foundation models will help us predict human behaviors for downstream tasks like intelligent embodied devices or human-robot interaction.
EgoVis Workshop CVPR 2025: Presentations on EgoLife, HaWoR, VidBot, and Discovering Visual Concepts Meta Open Source 2025-06-24 | 5-minute lightning talksTimestamps:- Intro: 00:00- Jiangkang Yang presents EgoLife: 00:19- Jinglei Zhang presents HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos: 06:35- Hanzi Chen presents VidBod: Learning Generalizable 3D Actions from in-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation: 12:05- Satoshi Tsutsui presents Discovering Hidden Visual Concepts Beyond LInguistic Input in Infant Learning: 19:05
EgoVis Workshop CVPR 2025: EPIC-KITCHENS and HD-EPIC Challenges Meta Open Source 2025-06-24 | The challenge results for EPIC-KITCHENS and HD-EPIC challenges are announced at CVPR 2025. Three selected talks are given from challenge winners. 1st Place: Angese Taluzzi presents From Pixels to Graphs: Using Scene and Knowledge Graphs for HD-EPIC VQA Challenge 2nd Place: Optimizing Multimodal LLMs for Egocentric Video Understanding: A solution for the HD-EPIC VQA Challenge
Introducing Pyrefly: A new type checker and IDE experience for Python Meta Open Source 2025-05-22 | Introducing a brand new open source project, Pyrefly. It's a blazing-fast Python type checker and IDE extension written in Rust. Pyrefly is a static type checker that analyzes Python code to ensure type consistency and help you catch errors throughout your codebase before your code runs. Learn more in an accompanying blog post: engineering.fb.com/2025/05/15/developer-tools/introducing-pyrefly-a-new-type-checker-and-ide-experience-for-python----- Resources ------ Pyrefly Website: pyrefly.orgPyrefly Github: github.com/facebook/pyreflyPyrefly Discord: discord.com/invite/Cf7mFQtW7WPyrefly VSCode Extension: marketplace.visualstudio.com/items?itemName=meta.pyrefly ------ Social Accounts ------Meta Open Source X Account: http://twitter.com/metaOpenSource Meta Open Source Threads Account: threads.com/@metaopensourceMeta Open Source Facebook Page: http://www.facebook.com/metaOpenSource Meta Open Source Website: http://opensource.facebook.com Meta Open Source LinkedIn Page: linkedin.com/showcase/78457036
Aria Gen 2 Case Study: Envision - Spatial Audio Navigation and AI Research (with audio descriptions) Meta Open Source 2025-03-04 | Explore the possibilities with Aria Gen 2 in our new case study with Envision and LightHouse SF (with audio descriptions).In collaboration with Lighthouse SF, Envision is exploring the integration of its Ally AI assistant and spatial audio using Aria Gen 2 glasses to improve navigation for individuals who are blind and have low vision.The team leverages the on-device SLAM capabilities of Aria Gen 2, along with spatial audio features via onboard speakers to give a user spatialized audio cues to guide them to products they need in a grocery store. This work is still in an exploratory phase, but exemplifies how partners can leverage the new capabilities of Aria Gen 2 glasses for prototyping AI experiences.Read the blog post to learn more about Aria Gen 2: meta.com/blog/project-aria-gen-2-next-generation-egocentric-research-glasses-reality-labs-ai-roboticsLearn more about Envision: letsenvision.comLearn more about LightHouse SF: lighthouse-sf.org Learn more about Ally AI: ally.me
Introducing Aria Gen 2 Meta Open Source 2025-02-27 | Since its launch in 2020, Project Aria has propelled research across the world to advance the state of the art in machine perception and AI, through access to cutting-edge research hardware and open-source datasets, models, and tooling. Today, we're excited to announce the next step in this journey: the introduction of Aria Gen 2 glasses. This next generation of hardware will unlock new possibilities across a wide range of research areas including machine perception, egocentric and contextual AI, and robotics.Read the blog post to learn more about Aria Gen 2: meta.com/blog/project-aria-gen-2-next-generation-egocentric-research-glasses-reality-labs-ai-roboticsLearn more about Project Aria: projectaria.comLearn more about the Project Aria datasets: projectaria.com/datasets
Project Aria Case Study: Introducing EgoMimic by the Georgia Institute of Technology Meta Open Source 2025-02-19 | Prof. Danfei Xu and the Robot Learning and Reasoning Lab (RL2) present EgoMimic. EgoMimic is a full-stack framework that scales robot manipulation through egocentric-view human demonstrations via Project Aria glasses. Read the blog post to learn more: ai.meta.com/blog/egomimic-project-aria-georgia-tech-ego4d-robotics-embodied-aiLearn more about the Aria Research Kit at projectaria.com.
RocksDB Meetup: 2024 End of Year Meta Open Source 2025-02-07 | Recording of our 2024 annual RocksDB meetup at Meta HQ. We have a collection of external speakers from both academia and industry including Timeplus, PayPal, and Arizona State University as well as internal presentations on features and optimizations the core RocksDB team has made over the past year. Timestamps:- Intro: 00:00- How Timeplus leverages RocksDB to do billions of keys streaming join and aggregation (Ken Chen - Timeplus): 03:02- Decoupled-RocksDB and Its Automatic Tuning with LLMs (Zhichao Cao - Arizona State): 23:47- Sally - A RocksDB Storage Management Plane (Dhanabal Ekambaram, Sushil Patil - Meta): 45:43- JunoDB - PayPal's Distributed Key-value Store (Yaping Shi - Paypal): 01:18:09- Multi-Column-Family Iterator in RocksDB (Jay Huh - Meta): 01:44:26- Multi-dimensional filtering in RocksDB (Peter Dillinger - Meta): 01:54:32- RocksDB stress/crash testing (Hui Xiao - Meta): 2:14:24Project LinksWebsite: http://rocksdb.orgGithub: github.com/facebook/rocksdbSocial AccountsRocksDB Facebook: facebook.com/rocksdbRocksDB X: https://x.com/rocksdbMeta Open Source X: http://x.com/MetaOpenSourceMeta Open Source Facebook Page: http://www.facebook.com/MetaOpenSourceMeta Open Source Website: http://opensource.facebook.comMeta Open Source LinkedIn: linkedin.com/showcase/meta-open-sourceMeta Open Source Threads: threads.net/@metaopensource
1st Workshop on EgoMotion - CVPR 2024 Meta Open Source 2024-10-22 | Watch the recording of the EgoMotion workshop from CVPR 2024. This workshop focuses on in-the-wild egocentric full-body motion understanding from data captured by wearable devices. We addressed three major problems for full-body motion -- tracking, synthesis and action recognition. The scope combines several topics and sub-fields that have grown in importance over the last years, and aims to bring these fields together in a common forum. Towards egocentric full-body tracking, motion synthesis and action recognition, we will focus on, but not limited to, algorithms developed for the following inputs.In addition to algorithms, the workshop promotes multiple recent datasets and associated challenges to accelerate research in this field.Learn more at: egomotion-workshop.github.ioOrganizers: Lingni Ma (Meta), Richard Newcombe (Meta), Yuting Ye (Meta), Edward Miller (Meta), Ziwei Liu (NTU), Yifeng Jiang (Stanford), Vladimir Guzov (University of Tübingen)Chapters (timecodes to be refined once uploaded)00:00:00 Richard Newcombe (Meta) - Opening00:13:47 Siyu Tang (Assistant Professor, ETH Zürich) - Egocentric 3D Human Estimation and Synthesis00:35:17 Christian Theobalt (Professor, MPI-IN) - Egocentric Human Motion Capture with Head-mounted Cameras01:04:51 Hanbyul Joo (Assistant Professor, Seoul National University) - Towards Capturing Everyday Movements to Scale Up and Enrich Human Motion Data01:31:01 Lingni Ma (Research Scientist, Meta) Yuting Ye (Research Scientist, Meta) - Nymeria: Understanding Human Motion from Egocentric Data02:02:12 C. Karen Liu (Professor, Stanford University), Jiaman Li (Ph.D Student, Stanford University) - Egocentric Perception for Human Motion Synthesis02:27:14 Gerard Pons-Moll (Professor, University of Tübingen) - How and Why Should We Learn Avatars with Sensorimotor Capabilities?02:55:24 Manuel Kaufmann (Postdoc, ETH Zurich) - Motion Capture with Electromagnetic Body-worn Sensors03:09:18 Fangzhou Hong (Ph.D Student, NTU) - EgoLM: Multi-Modal Language Model of Egocentric Motions03:22:02 Xinyu Yi (Ph.D Student, Tshinghua University) - Egocentric Motion Capture with Sparse Inertial/Visual Sensors#CVPR2024 #ARIA
Third Egocentric Research Tutorial with Project Aria – ECCV 2024 Meta Open Source 2024-10-17 | Watch the recording of the Third Egocentric Research Tutorial with Project Aria, where we introduced new features of the Aria Research Kit (ARK) and Open Science Initiatives (OSI), shared novel research from academic partner program members, described how researchers can gain access to the Project Aria academic program, and introduced new open datasets for accelerating machine perception research.This workshop is a great opportunity to learn about the latest developments in egocentric perception and how Project Aria is helping to accelerate research in this field. Learn more at: http://www.ProjectAria.comOrganizers: James Fort (Meta), Richard Newcombe (Meta), Edward Miller (Meta), Kristen Grauman (Meta)Chapters00:00:00 James Fort (Meta) - An Update to the Aria Research Kit and Open Science Initiatives00:25:22 Xiaqing Pan (Meta) - Aria Live Demo00:41:09 Yang Lou (Meta) - Aria Training and Evaluation Kit (ATEK)00:54:52 Dr. Zhao Dong (Meta) - Digital Twin Catalog dataset01:27:30 Dr. Prithviraj Banerjee (Meta) - HOT3D dataset for hand-object interaction understanding01:42:02 Dr. Lingni Ma (Meta) - Nymeria dataset for egocentric human motion understanding01:57:16 Dr. Julian Straub (Meta) - EFM3D dataset for 3D egocentric foundation models02:10:53 Dr. Antonino Furnari (University of Catania) - Ego-Exo4D Overview02:34:25 Prof. Dima Damien (University of Bristol) - Egocentric Recording in the Home02:50:39 Dr. Francesco Ragusa (University of Catania) - EFM3D dataset for 3D egocentric foundation models03:01:25 Dr. Paul-Edouard Sarlin (ETH Zurich) - LaMar Aria3:26:16: James Fort (Meta) - Concluding Remarks#ECCV2024 #ARIA
Project Aria Case Study: Carnegie Mellon University Meta Open Source 2024-10-16 | In this video, Kris Kitani, Associate Research professor at the Robotics Institute at Carnegie Mellon University, describes how Project Aria supported the development of ‘Navcog’, a mobile application, designed to solve the challenge of indoor location, and provide audio wayfinding to people who are visually impaired.By working with Project Aria, CMU were able to reduce their dependence on bluetooth beacons, and bring new environments online at a faster rate, enabling NavCog to be available to more people who need it.Learn more about Project Aria and the Aria Research Kit at projectaria.com
9th Workshop on Recovering 6D Object Pose (R6D) - ECCV 2024 Meta Open Source 2024-10-11 | Watch the recording of the 9th Workshop on Recovering 6D Object Pose (R6D), held at ECCV 2024. The workshop focuses on the latest advances in model-based and model-free 6DoF object pose estimation, with applications in augmented reality, robotic manipulation, and autonomous driving. Featuring four invited talks by experts in the field and presentation of the BOP Challenge 2024, this recording is a valuable resource for researchers and practitioners working on related topics.Organizers: Tomas Hodan (Meta), Martin Sundermeyer (Google), Van Nguyen Nguyen (ParisTech), Stephen Tyree (NVIDIA), Andrew Guo (University of Toronto), Médéric Fourmy (CTU in Prague), Anas Gouda (TU Dortmund), Taeyeop Lee (KAIST), Sungphill Moon (NAVER LABS), Hyeontae Son (NAVER LABS), Lukas Ranftl (MVTec), Jonathan Tremblay (NVIDIA), Yann Labbé (Meta), Eric Brachmann (Niantic), Bertram Drost (MVTec), Sindi Shkodrani (Meta), Carsten Steger (TUM, MVTec), Vincent Lepetit (ParisTech), Carsten Rother (Heidelberg University), Stan Birchfield (NVIDIA), Jiri Matas (CTU in Prague)Chapters:00:00:00 Introduction: Tomas Hodan (Meta)00:08:20 Talk 1: Detector-free feature matching for pose estimation - Xiaowei Zhou (Zhejiang University)00:36:57 Talk 2: Relaxing pose estimation: Unseen objects and visual challenges - Benjamin Busam (TUM)01:05:17 Talk 3: Practical robotic scene awareness - Stan Birchfield (NVIDIA)01:34:14 Talk 4: Towards Contextual AI: Tracking objects and our interactions with them - Jakob Engel (Meta)02:02:07 BOP 2024: Introduction - Tomas Hodan (Meta)02:17:00 BOP 2024: HANDAL dataset - Stephen Tyree (NVIDIA)02:19:31 BOP 2024: HOPEv2 dataset - Stephen Tyree (NVIDIA)02:23:10 BOP 2024: HOT3D dataset - Prithviraj Banerjee, Sindi Shkodrani (Meta)02:32:08 BOP 2024: Estimating object visibility on HOT3D - Taeyeop Lee (KAIST)02:36:21 BOP 2024: Challenge tracks - Van Nguyen Nguyen (ParisTech)02:43:40 BOP 2024: Results and early-bird awards - Martin Sundermeyer (Google), Van Nguyen Nguyen (ParisTech)02:54:10 BOP 2024: GenFlow results on BOP-H3 - Sungphill Moon (NAVER LABS)02:58:59 BOP 2024: BOP-Robotics - Martin Sundermeyer (Google)#ECCV2024 #BOP
Project Aria Case Study: IIIT Hyderabad Meta Open Source 2024-10-09 | In this video, Avijit Dasgupta, Ph.D student of Computer Vision at IIIT Hyderabad gives an overview of his research with the CVIT lab in collaboration with Project Aria. Dasgupta's team is working on the Driver Intent Prediction project, a computer vision application for accident prediction.Learn more about Project Aria and the Aria Research Kit at projectaria.com
Project Aria Case Study: University of Iowa Meta Open Source 2024-10-09 | In this video, two professors from the Unversity of Iowa; Yu-Hsiang Wu, M.D. Ph.D., an Associate Professor of Communication Sciences and Disorders, and Octav Chipara, Ph.D., a Professor of Computer Science, provide an overview of their collaboration with Project Aria to build contextually aware hearing-aid technology. Learn more about Project Aria and the Aria Research Kit at projectaria.com
Project Aria Case Study: University of Bristol Meta Open Source 2024-10-09 | In this video, Dima Damen Ph.D., professor of Computer Vision at the University of Bristol provides an overview of her work in collaboration with Project Aria and Ego-Exo4D. Join Project Aria's academic research community, and apply for an Aria Research Kit. Learn more about Project Aria and the Aria Research Kit at projectaria.com
Introducing the Project Aria Research Kit Meta Open Source 2024-10-09 | In this video, Project Aria from Meta Reality Labs presents the Aria Research Kit. The Aria Research Kit (ARK) is a research ecosystem, available for approved research partners. ARK partners use Project Aria glasses and tools for a broad range of research topics, including embodied AI, contenxtualized AI, HCI, robotics and more. The time to apply for an Aria Research Kit is now, learn more about Project Aria and the Aria Research Kit at projectaria.com
RocksDB Meetup: 2023 End of Year Meta Open Source 2024-01-25 | This is a recording of an annual RocksDB meetup at the Meta HQ in Menlo Park, California. We had a collection of external speakers from academia and industry, including Cloudera, Pinterest, the University of Washington, and PingCap, and internal presentations on the expansion of RocksDB’s vision and tuning optimizations we’ve made over the past year. Below is the list of talks:- Our experience with using RocksDB in TiKV by PingCap (Sunny Bain)- Key Value Unification at Pinterest (Rajath Prasad)- RocksDB Vision Expansion by Meta (Danny Chen)- An efficient RocksDB Checkpoint Diff Mechanism by Cloudera (Prashant Pogde)- Tuning Optimizations on RocksDB Scans by Meta (Akanksha Mahajan)- Dremel - Adaptive Configuration Tuning of RocksDB KV-Store by University of Washington (Frank Zhao)Project LinksWebsite: http://rocksdb.orgGithub: github.com/facebook/rocksdbSocial AccountsRocksDB Facebook: facebook.com/rocksdbRocksDB Twitter: twitter.com/rocksdbMeta Open Source Twitter: http://twitter.com/MetaOpenSourceMeta Open Source Facebook Page: http://www.facebook.com/MetaOpenSourceMeta Open Source website: http://opensource.facebook.com
Project Aria CVPR 2023 Tutorial: Aria Digital Twin Dataset (Section 8 of 10) Meta Open Source 2023-10-09 | In this video, research director Carl Ren gives an overview of the Aria Digital Twin dataset, and introduces new research challenges for object detection and tracking.Recorded June 2023 during the CVPR 2023 Tutorial entitled 'Hands-on egocentric research with Project Aria, from Meta'Learn more at ProjectAria.com
Project Aria CVPR 2023 Tutorial: EgoHuman Dataset from CMU (Section 10 of 10) Meta Open Source 2023-09-11 | In this video, research scientist Rawal Khirodkar gives an overview of the EgoHuman dataset from CMU.Recorded June 2023 during the CVPR 2023 Tutorial entitled 'Hands-on egocentric research with Project Aria, from Meta'Learn more at ProjectAria.com
Project Aria CVPR 2023 Tutorial: Aria Synthetic Environments Dataset (Section 9 of 10) Meta Open Source 2023-09-11 | In this video, research scientist Christopher Xie gives an overview of the Aria Synthetic Environments dataset, and introduces new research challenges for scene reconstruction.Recorded June 2023 during the CVPR 2023 Tutorial entitled 'Hands-on egocentric research with Project Aria, from Meta'Learn more at ProjectAria.com
Project Aria CVPR 2023 Tutorial: Open Science Initiatives (Section 7 of 10) Meta Open Source 2023-09-11 | In this video, research product manager Edward Miller gives an overview of Meta's open-source tools, models, and datasets, including the announcement of Aria Digital Twin, and Aria Synthetic Environments datasets.Recorded June 2023 during the CVPR 2023 Tutorial entitled 'Hands-on egocentric research with Project Aria, from Meta'Learn more at ProjectAria.com
Project Aria CVPR 2023 Tutorial: Live Demo (Section 6 of 10) Meta Open Source 2023-09-11 | In this video, software engineer Vijay Baiyya gives a live demonstration of the Project Aria tooling, demonstrating the visualization of device sensor data, trajectory, point cloud, and eye gaze.Recorded June 2023 during the CVPR 2023 Tutorial entitled 'Hands-on egocentric research with Project Aria, from Meta'Learn more at ProjectAria.com
Project Aria CVPR 2023 Tutorial: Software Ecosystem Overview (Section 5 of 10) Meta Open Source 2023-09-11 | In this video, research director Carl Ren provides an overview of the Project Aria software ecosystem, including client applications, SDK, and system services.Recorded June 2023 during the CVPR 2023 Tutorial entitled 'Hands-on egocentric research with Project Aria, from Meta'Learn more at ProjectAria.com
Project Aria CVPR 2023 Tutorial: Machine Perception Services (Section 4 of 10) Meta Open Source 2023-09-11 | In this video, research director Jakob Julian Engel provides an overview of the machine perception services provided by Meta to automatially derive new annotations from egocentric data, including pose estimation, semi-dense pointcloud generation, eye gaze estimation, and hand pose estimation.Recorded June 2023 during the CVPR 2023 Tutorial entitled 'Hands-on egocentric research with Project Aria, from Meta'Learn more at ProjectAria.com
Project Aria CVPR 2023 Tutorial: Overview of Aria Research Kit (Section 3 of 10) Meta Open Source 2023-09-11 | In this video, research product manager Sach Lakhavani introduces the set of tools provided by Meta to enable external researchers to work with Project Aria glasses.Recorded June 2023 during the CVPR 2023 Tutorial entitled 'Hands-on egocentric research with Project Aria, from Meta'Learn more at ProjectAria.com
Project Aria CVPR 2023 Tutorial: Introduction to Project Aria (Section 2 of 10) Meta Open Source 2023-09-11 | In this video, research product manager Prince Gupta introduces Meta's research program for accelerating AI and Machine perception research "Project Aria".Recorded June 2023 during the CVPR 2023 Tutorial entitled 'Hands-on egocentric research with Project Aria, from Meta'Learn more at ProjectAria.com
Project Aria CVPR 2023 Tutorial: Introduction to Always On Machine Perception (1 of 10) Meta Open Source 2023-09-11 | In this video, research director Richard Newcombe introduces the motivations and challenges related to all-day wearable computing.Recorded June 2023 during the CVPR 2023 Tutorial entitled 'Hands-on egocentric research with Project Aria, from Meta'Learn more at ProjectAria.com
Project Aria CVPR 2023 Tutorial Highlights Meta Open Source 2023-09-11 | Highlights of the CVPR 2023 Tutorial entitled 'Hands on egocentric research with Project Aria, from Meta', recorded June 2023.Learn more about Project Aria at www.projectaria.com
The Diff Episode 17: How the team realized Presto could be faster Meta Open Source 2023-06-27 | Developer Advocate Philip Bell interviews Software Engineer Masha Basmanova and they discuss Velox, the #OpenSource unified engine aimed at accelerating data management and why C++ was the language of choice.Listen to the full podcast here: thediffpodcast.com/docs/episode-17------ Resources ------The Diff Podcast: thediffpodcast.com/docs/episodes ------ Social Accounts ------Meta Open Source Twitter: http://twitter.com/metaOpenSource Meta Open Source Facebook Page: http://www.facebook.com/metaOpenSource Meta Open Source Website: http://opensource.facebook.com Meta Open Source LinkedIn Page: linkedin.com/showcase/78457036
The Diff Episode 17: What you can use Velox for and what you shouldnt Meta Open Source 2023-06-20 | Developer Advocate Philip Bell interviews Software Engineer Masha Basmanova and they discuss the Open Source unified engine Velox, and how developers can use Velox in their workflow, along with what to avoid.Listen to the full podcast here: thediffpodcast.com/docs/episode-17------ Resources ------The Diff Podcast: thediffpodcast.com/docs/episodes ------ Social Accounts ------Meta Open Source Twitter: http://twitter.com/metaOpenSource Meta Open Source Facebook Page: http://www.facebook.com/metaOpenSource Meta Open Source Website: http://opensource.facebook.com Meta Open Source LinkedIn Page: linkedin.com/showcase/78457036
