.@BigscreenVR x @VRChat Giveaway!
We’re giving away 1 Bigscreen Beyond 2e: VRChat Edition + 10 Years of VRC+! 🎉
To enter: RT this post.
No purchase necessary. Open to eligible participants.
Full rules: https://t.co/myn4OQp9gM
Ends Sept 8 at 11:59pm PST.
Meet MapAnything – a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art results 🚀
One universal model enables SoTA for:
🔥 Mono Depth Estimation
🔥 Multi-View SfM
🔥 Multi-View Stereo
🔥 Depth Completion
🔥 Registration
… and many more possibilities! – plus everything is metric 🎯
We release code for data processing, training, benchmarking & ablations – everything Apache 2.0!
Details & Links 👇
LichtFeld Studio in Action! GPLv3 - no subscriptions, no data scraping, forever free!
- Trains in 20 minutes at 4k for 60k steps with 2m Gaussians and MCMC densification.
- With enabled bilateral guidance (CUDA version), it totals 60 minutes.
- Pretty much floater free.
Makes me quite proud of what we have achieved in not even 2 months!
Features:
- The world's fastest training!
- Supports MCMC and ADC
- Pose Optimization
- Bilateral Guidance
- Train on distorted images with 3DGUT
- Multi-ply viewing
- Live training preview
This isn't even something you could call a beta or alpha version. This wouldn't have been possible without contributions from the wonderful 3DGS community. We are transparent, and everything is open.
There is much more to come! Be part of it and start contributing today!