Pinned
Rerun
1,713 posts
The data layer for physical AI.
β GitHub github.com/rerun-io/rerun
πΎ Discord discord.gg/ZqaWgHZ2p7
Joined December 2021
- π§΅1/ Weβre very excited about SimpleRecon! It brings together state-of-the-art depth accuracy and competitive 3D scene reconstruction which makes it perfect for resource-constrained environments! We used @rerun to dig into its inner workings. #computervision #AI #ML
00:00 - The upcoming Rerun 0.17 brings a huge increase in explicit control over your visualizations π In this video for example we dynamically change the visualizer that is applied on an entity from Mesh3D to Points3D and then edit the radius of the points. Because this mesh has vertex
00:00 - SimpleRecon in Rerun 0.16! SimpleRecon is a back-to-basics approach for 3D scene reconstruction from posed monocular images by @NianticLabs . It offers state-of-the-art depth accuracy and competitive 3D scene reconstruction, which makes it perfect for resource-constrained
00:00 - Sim-to-Rerun: Using Rerun to visualize CARLA simulator output through #ROS 2. This example visualizes simulated sensor data from the CARLA simulator for autonomous driving in Rerun. Itβs built using Rerunβs new proof-of-concept C++ ROS2 bridge, which currently has support for a
00:00 - Visualize GLOMAP in Rerun! GLOMAP is a general purpose global structure-from-motion pipeline for image-based sparse reconstruction. As compared to COLMAP it provides a much more efficient and scalable reconstruction process, typically 1-2 orders of magnitude faster, with on-par
00:00
π 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! π It's faster and more accurate than COLMAP on several datasets. π Website: lpanaf.github.io/eccv24_glomap/ @mapo1, @LinfeiPan, J. SchΓΆnberger - Much of our communication around Rerun has been focused on computer vision and robotics use cases, but we have always thought of it as more general purpose than that. We want to give users the ability to easily visualize any multimodal data.
00:00 - Introducing Rerun 0.13! With this release Rerun is (to our knowledge) the first publicly available multimodal visualizer with timeline scrolling that supports live visualization of time series in the kHz range. This is made possible by a 20-30x performance increase of time
00:00 - Go2 in Rerun: visualizing @UnitreeRobotics Go2 quadruped using Rerunβs ROS 2 bridge PoC. This example visualizes the Go2 robot, its onboard sensor data, and how it sees the environment. Itβs built using Rerunβs new proof-of-concept C++ ROS 2 bridge, which currently supports a
00:00 - Rerun 0.20 is out! πΊππ₯ It adds early support for geospatial data with the new GeoPoints and GeoLineStrings archetypes and a map view. It also adds H.264 video support to the native viewer together with many performance and stability improvements for video in Rerun.
00:00 - We're hiring a Senior Rust Backend Engineer! π¦
- π‘ Visualization is to Physical AI data whatΒ printΒ is to text. It needs to be availableΒ everywhere, in all layers of the stack, for data in all forms.
00:00 - Robots in Rerun, a glimpse of things to come! π€ πΌ This example shows @BostonDynamics Spot robot by combining its URDF and onboard sensor data. It is built using Rerunβs proof-of-concept C++ ROS1 bridge, which now works for limited use cases. For all you roboticists: Rerun is,
00:00 - Check out the Neural Graph Mapping for Dense SLAM with Efficient Loop Closure paper by @leonard_bruns, Jun Zhang, and Patric Jensfelt, visualized with Rerun. βExisting neural field-based SLAM methods typically employ a single monolithic field as their scene representation. This
00:00


