Things took a bit longer than I hoped. But here is the first part of the reimplemented VistaDream Pipeline, visualized with Rerun. Repo ⬇︎ I took a photo of my office and ran it through the pipeline. I think it came out pretty well! Just as a reminder, this current

it just has to look cool, right?

Tired of static plots that can't keep up with your dynamic CV data? Explore how Rerun is revolutionizing interactive visualization for computer vision projects in Florian Trautweiler's insightful analysis. towardsdatascience.com/interactive-da…

Trying to add some more debuggability to this. Took a picture of my living room and dog. Rerun makes visualizing splats over time easier, but I have to use point clouds as a representation for now as there's no native splatting support yet. I want to visualize the splat

Some more updates on the image -> splat pipeline visualized with Rerun 🖼️➡️✨ I did a lot more with blueprints to try to make things easier to understand and visually pleasing 🎨 I also wanted to get things working really well with the single image version before moving on

Our own gijs and his Dutch Nao Team are killing it at the World Humanoid Robot Games! They, of course, rebuilt their stack from the ground up in Rust and are using Rerun.

Some updates on the multiview vistadream pipeline with Rerun! Rerun came in extremely useful here, as being able to visualize depths at each stage of the pipeline allowed me to debug some nasty bugs. Since the last time, I was only working with a single image input.

Pranay Thangeda Ishan Khatri Rerun Rerun is incredible.

Real-Time Stereo Matching with retinify! 🚀 Try it on GitHub: github.com/retinify/retin… Features: ✅ Open Source ✅ Works with any stereo camera ✅ Real-time performance on NVIDIA Jetson Orin Nano With retinify, even inexpensive OEM stereo cameras—or a pair of mono cameras—can

Will they score? Follow along with this on-board recording of the Dutch Nao Team during the World Humanoid Robot Games. Rerun is a proud sponsor of the team.

This is a big one! I'm almost done with my MVP, built with Rerun and Gradio! TLDR: Inputs - 2-N Synchronized Videos in a zip file Outputs - Multiview Consistent Depthmaps + Pointclouds (Thanks VGGT + MogeV2!) - Depth Confidence Values - Camera calibration parameters