Mike Dopsa

Say less, do more. All in on immersive

[Mike Dopsa @MCDopsa]

@Dilmerv Awesome, thanks! I’ve also had best results with small tasks, individual components, and coordinate space conversion as well.

[Yannick Comte @cyannick]

I spent 45 minutes trying to do PCVR on Windows with Meta Link and them ALVR. Starting VR should be instant, if an error occurs, the user have to know why and how to fix it.
That's why I'm making oxrsys a crossplatform openxr runtime, not just for macos, but also for Linux and Windows, for both x64 and arm64 targets.

[Mike Dopsa @MCDopsa]

@tom_krikorian Ok good to know about baking! I wasn’t sure if a whole graph would carry over into MaterialX or shadergraph equivalents

[Mike Dopsa @MCDopsa]

@pvncher @OpenAI @romainhuet @RepoPrompt Congrats Eric, excited to see what you get up to there

[Mike Dopsa @MCDopsa]

@XRarchitect One day, with a lightfield display & camera we’ll get this for real🤞🏻

[Yannick Comte @cyannick]

To make things simpler, I've uploaded binaries
- The runtime (signed but not notarized), like the OVRService.exe
- The compagnon, like the Meta Link App
- The simulator to test without an headset
- The Quest player (APK)
https://t.co/jKvQcGTWix
Have fun doing VR on MacOS

[Lucas Martinic @lucas_martinic]

13/100 "What if we could tear down reality?"

Inspired by @pushmatrix's https://t.co/7YDiKKXT6f

[MrNeRF @janusch_patas]

I'm excited to share the Geo Register Plugin for LichtFeld Studio from the LichtFeld community!

This plugin helps bring Gaussian splat scenes into real-world geographic space. It registers a scene to WGS-84 and ECEF coordinates, so you can click any point on the model and get its latitude, longitude and altitude.

It supports multiple georeferencing sources, including EXIF GPS data, image position CSVs, RealityScan camera parameters and saved similarity transforms. Once the scene is registered, you can export geo-referenced splat models as LAS, LAZ or 3D Tiles datasets for use in GIS and 3D mapping workflows.

Built for anyone working with drone data, photogrammetry, Gaussian splatting, GIS, ArcGIS or CesiumJS.

Link in the comment below!

[Mike Dopsa @MCDopsa]

@XRarchitect Very nice! Scan or 360 image of the living room space as bg?

[Sadao Tokuyama @tokufxug]

画像と3Dデータの共通する位置を特定するAI「UniCorrn」が登場。

従来はデータの種類ごとに別のAIが必要でしたが、一つの仕組みで処理を統一。

その結果、従来手法を8%〜10%上回る精度で、写真と立体データ間の正確な位置合わせを可能にするAI技術です。

[Mike Dopsa @MCDopsa]

@xchester16 Looking forward to it, happy to test if you need feedback. Will you also make it a development tool, or is it based on an existing renderer?

[Mike Dopsa @MCDopsa]

For the first time, I’m going to WWDC! Excited to meet other Vision Pro developers and creators. If you’re attending or will be in the area, let’s chat!

[Mike Dopsa @MCDopsa]

@xchester16 Thank you, will you be going as well? Your GS work on AVP is really exciting!

[Gábor Pribék @gaborpribek]

Physics via OS window shake is so much fun! Original scene by @mrdoob and physics exploration by @goncalotex made in @omma_ai

[Mike Dopsa @MCDopsa]

@Azadux @LKGGlass Dang, I also didn’t realize this was possible. I thought it was old iPad screens they used for these

[Ning Yu @realNingYu]

📢 Eyeline Labs and Netflix’s latest research, 🎥Vista4D🎥, accepted at #CVPR2026 as a 🌟Highlight🌟 paper, advances virtual cinematography and scene control with video generation.
🎥 Vista4D synthesizes the dynamic scene represented by an input video from novel camera trajectories and viewpoints by grounding video generation in a 4D point cloud. Our method maintains geometric and physical plausibility under imprecise 4D reconstruction of real-world videos.
🎥 Vista4D unlocks video reshooting beyond camera control. By directly editing the 4D point cloud, our method preserves scene information from casual captures and enables 4D scene editing and recomposition.

This work is part of the ongoing research and development at @eyelinestudios and @netflix, and we look forward to seeing its techniques and workflows adopted in future productions.
✊ Kudos to the team: @kuanhenglin, Zhizheng Liu, @pablosalamancal, @yash2kant, @RyanBurgert, @Yuancheng_Xu0, @Koichi_N_, Yiwei Zhao, @zhoubolei, @micahgoldblum, @debfx, @realNingYu

📰 Paper: https://t.co/PsuWi1xQqs
🌐 Project: https://t.co/SoUJW1krO1
⌨️ Code: https://t.co/vcbfeqIJ3o

[Mike Dopsa @MCDopsa]

@TinaDebove With cross compatibility to iOS 🤞🏻

[Mike Dopsa @MCDopsa]

@nandoprince93 @_willcompton @BussinWTB Pickle Pro with those controllers is great

[spark @sparkjsdev]

Spark 2.0 is here! 🚀

We’re redefining what’s possible on the web with a streamable LoD system for 3D Gaussian Splatting.

Built on Three.js, you can now stream massive 100M+ splat worlds to any device from mobile to VR using WebGL2. All open-source.

Dive into the tech 👇