How do you make AI-generated 3D shapes editable? Break them into smart building blocks. Our #CVPR2026 Oral SuperFit converts 3D shapes into compact, editable primitive assemblies with SuperFrustum, an 8-parameter primitive that spans cubes, cones & more. https://t.co/7bqiVSISM9 #3D
Introducing TripoSplat: a fully open-sourced model under the MIT license that converts a single 2D image into high-quality 3D Gaussians.
Developed by @vastairesearch, TripoSplat is designed as a powerful pipeline tool for asset creation, AR/VR, game development, simulation environments, and more 👇
Do 3D reconstruction transformers really need a billion parameters, or are most of those layers just doing the same thing over and over?
Introducing Déjà View: a single transformer block, looped K times, that matches or beats models 8–10× its size with lower compute. 🧵
What if you could combine the precision of classical Structure-from-Motion with the local robustness of feedforward 3D models?
Meet GLUEMAP — a CVPR 2026 highlight ✨ SOTA across 5 datasets spanning 6 challenges.
w/ @ahojnnes & @mapo1
🌐website: https://t.co/pEh8jQh1ZN
📢📢GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction📢📢
Reconstructing high-fidelity 3D scenes from sparse RGB input is hard. It needs a strong 3D prior!
We reformulate multi-view scene reconstruction as conditional 3D generation over overlapping spatial chunks, lifting posed image features into a generative shape prior via 3D conditioning. As an example prior, we build on Trellis2, and train it such that its reconstruction is pixel aligned and matches from all views.
GenRecon achieves unprecedented reconstruction quality from any sparse RGB input sequence, even from a phone capture. The reconstruction also includes PBR materials which facilitates relighting and virtual object insertion.
https://t.co/1RMD40WRpz
https://t.co/u4IEi5PTtn
Amazing work by @katha_schmid, @nicolasvluetzow, Jozef, @angelaqdai
Introducing VGGT-Ω: scaling feed-forward reconstruction across static and dynamic scenes, and studying whether the learned geometric representations transfer beyond reconstruction.
All your favorite 3D models — now faster with Co-Me.
🎉 Accepted to CVPR 2026, Co-Me now supports more 3D foundation models: MapAnything 1.1, Depth Anything 3, and Pi3.
Same simple confidence-guided token merging idea — now accelerating even more 3D reasoning models. 👇
Build Faster, Earn More.
That's what we're focused on over the next two months for developers building with Meta Quest. New tools, new playbooks, new case studies. 💡
Here's what's rolling out now and what's coming next 👉 https://t.co/v600VHU7ED
At a glance 🧵👇
3 major SuperSplat upgrades shipping today 🚀
🧱 One-Click Collision Generation
We've wired the SplatTransform 2.0 collision pipeline into SuperSplat Studio's backend.
Open your splat ➡️ Assets panel ➡️ Hit Generate
Walk-ready splats in seconds. No command line. No fuss.
[1 / 4]