
Not posting here anymore. mastodon: https://nitter.gq/t.co/wjge4MN77I bsky: @wumpf.bsky.social
Joined July 2011
- Tweets954
- Following187
- Followers555
- Likes1.6K
AndreasR retweeted
Tried out the new video support in @rerundotio 0.19 by visualizing @Apple's DepthPro model with @Gradio on @huggingface Spaces. Super cool to see it in action!
oxkitsune-rerun-ml-depth-pro…
AndreasR retweeted
Video support for the upcoming 0.19 release is coming along nicely 🎥 👀
For this release it will be limited to the web viewer, only mp4 containers (no streaming yet), and supporting AV1 and H.264. But we're just getting started.
Stay tuned!
AndreasR retweeted
I can't believe we're done!
Time Ghost
A short film we on the Demo Team have been working on for a while
youtu.be/o1JIK5W3DRU
Like all our team’s demos, it runs in real-time at 30fps in Unity. Over the next days I’ll be posting rendering and tech art breakdowns in this 🧵
AndreasR retweeted
Rerun 0.18: Columnar API and new data architecture for faster writes & ingestion + lower memory use.
This release brings orders of magnitude faster writes and ingestion times and lower memory usage for many long time-series datasets. It’s powered by a new column chunk based architecture. The new rr.send_columns APIs makes it easier and faster to send pre-recorded data to Rerun without having to log it.
For good measure, we also threw in mesh and 3D shape instancing through the InstancePose archetype as well as a new shape primitive for 3D ellipsoids.
0.18 is another big step forward on our quest to help robotics and embodied AI teams unify their visualization and data stacks by making Rerun fly through even more kinds of datasets!
AndreasR retweeted
The upcoming Rerun 0.17 brings a huge increase in explicit control over your visualizations 🚀
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 colors, the point cloud automatically becomes colored as well. All of this can be done either from UI or from code.
We’ll release 0.17 next week. Stay tuned.
AndreasR retweeted
HOT3D in Rerun! 🫱⌨️🫲
HOT3D is a new benchmark dataset for vision-based understanding of 3D hand-object interactions by @TweetEdMiller and the Project Aria team at @AIatMeta.
AndreasR retweeted
Rerun 0.15 is out! With it we’re introducing Blueprint APIs
With the new APIs you can define the layout and contents of views directly from code. For example, this video shows live coding of how the output of a face-tracking algorithm is shown as the algorithm is running.
Let’s dig in 👇
AndreasR retweeted
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 series plots.
AndreasR retweeted
Most of what teams build with @rerundotio ends up being proprietary but here are a couple public examples I love (in no particular order):
First off nitter.gq/rerundotio/status/1745…
Check out the Rerun visualization on this open dataset from @Meta's Project Aria! It combines human and Aria device pose, user eye gaze, and static and dynamic objects. The timeline only shows events when a dynamic object is moving. Changing the visible time range allows you to see past and future motion of a given object.
AndreasR retweeted
Rerun 0.11!
This release brings all SDKs to parity (Rust/Python/C++). It adds "Visual Time Range" queries to set the start and end of the time range to include in a visualization. And we now publish the Rerun web viewer as an NPM package to make it easy to integrate.
AndreasR retweeted
Replying to @PickNikRobotics
This looks really cool! Glad you liked our video 😉
nitter.gq/ernerfeldt/status/1625…
AndreasR retweeted
The upcoming 0.9 release will be a big one! We’re revamping our apis to be more powerful and consistent across languages (C++ is coming in 0.10). On first glance, the change seems small but it opens up for a lot more control and extensibility. Check it out 👇
AndreasR retweeted
Finding a textured mesh decomposition from a collection of images is a very challenging optimization problem. “Differentiable Block Worlds” by @t_monnier et al. shows impressive results using differentiable rendering. I visualized how the optimization works using @rerundotio.
Thanks for the highlight @_akhaliq!! Super happy to share this exciting work done with Jake Austin, @akanazawa, Alyosha Efros and Mathieu Aubry :) More details at tmonnier.com/DBW
AndreasR retweeted
🚀 Introducing Rerun 0.8!
Rerun is an easy-to-use visualization toolbox for computer vision and robotics.
This release adds customization features, transform improvements, lots of bug fixes, and first signs of infrastructure investments that will unlock powerful new features!
AndreasR retweeted
Tracking any point in a video is a fundamental problem in computer vision. The recent @DeepMind paper TAPIR by @CarlDoersch et al. significantly improved over prior state-of-the-art. I visualized the main components of their approach using @rerundotio.
AndreasR retweeted
Today's Rust Gamedev Meetup is starting in just 15 minutes! Here's today's schedule:
@aryanpur_elham - Blue Engine
@wumpf - ReRun
@GraphiteEditor - Graphite
#rustlang
AndreasR retweeted
🧵1/ We’re 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
AndreasR retweeted
Anybody knows the ETA for Safari getting WebGPU support? Also ETA for WebGPU on Android Chrome?
Congrats @ChromiumDev on shipping @WebGPU support! 🎉
At @rerundotio we’re building the next generation of computer vision and robotics tooling. WebGPU allows us to bring demanding rendering & compute workflows to the web!
#computervision #robotics #opensource #webgpu #wgpu
AndreasR retweeted
Huh, this is a neat use case for @rerundotio: parsing Starcraft 2 replays to understand how different strategies play out over time. Love it 😍youtube.com/watch?v=e5cTn8CZ…













