Happy to share that our paper was accepted as spotlight NeurIPS Conference 2024! See you in Vancouver 🇨🇦

SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving Georg Hess, Carl Lindström, Maryam Fatemi, Christoffer Petersson, Lennart Svensson tl;dr: 3DGS->rolling shutter+lidar intensity+ray dropping+variations arxiv.org/pdf/2411.16816

Introducing 🛹 RollingDepth 🛹 — a universal monocular depth estimator for arbitrarily long videos! Our paper, “Video Depth without Video Models,” delivers exactly that, setting new standards in temporal consistency. Check out more details in the thread 🧵

I’ll present our #NeurIPS2024 Spotlight Poster on Friday, 13 Dec 4:30-7:30pm PST in East Exhibit Hall A-C, booth #1505. Please step by to talk large-scale dynamic 3D Gaussians! :)

That‘s a wrap! Thanks to the organizers of NeurIPS Conference for putting together an amazing conference. See you soon Vancouver (what a beautiful venue!) 🛫

Today OpenAI announced o3, its next-gen reasoning model. We've worked with OpenAI to test it on ARC-AGI, and we believe it represents a significant breakthrough in getting AI to adapt to novel tasks. It scores 75.7% on the semi-private eval in low-compute mode (for $20 per task

As we learn to use compute more efficiently, we will use more compute.

✨We introduce SuperDec, a new method which allows to create compact 3D scene representations via decomposition into superquadric primitives! Webpage: super-dec.github.io ArXiv: arxiv.org/abs/2504.00992 Boyang Sun Francis Engelmann Marc Pollefeys CVG ETH AI Center

Watch MP-SfM crush VGGT and Mast3r-SfM! Great work on leveraging monocular priors to tackle some of the most challenging problems in SfM (low-overlap, low-parallax, symmetries) 👏

The time for new architectures is over? Not quite! SeNaTra, a native segmentation backbone, is waiting, let's see how it works 🧵arxiv.org/abs/2505.16993

📢 Introducing GenSfM – a generic Structure-from-Motion pipeline built on COLMAP, with smooth, invertible, and universal calibration for diverse cameras — from pinhole to catadioptric! Thanks Yihan_Wang Viktor Larsson Marc Pollefeys for the great collaboration. 🔗 ivonne320.github.io/yihan.home/Gen…

Monocular Dynamic Reconstruction is HARD! Single video input –> A LOT of 3D ambiguity –> Significant visual artifacts. BulletGen solves this using Generative Models, at various frozen ‘bullet-times’, fixing visual artifacts + filling-in missing info == much better results!

🌊🏄

Great opportunity to build cool stuff with brilliant minds.

This aged pretty well!

[1/N] 🎥 We've made available a powerful spatial AI tool named ViPE: Video Pose Engine, to recover camera motion, intrinsics, and dense metric depth from casual videos! Running at 3–5 FPS, ViPE handles cinematic shots, dashcams, and even 360° panoramas. 🔗 research.nvidia.com/labs/toronto-a…