FastMap: Revisiting Dense and Scalable Structure from Motion Jiahao Li, Haochen Wang, Zubair Irshad, Igor Vasiljevic, Matthew R. Walter, Vitor Campagnolo Guizilini, Greg Shakhnarovich tl;dr: replace BA with epipolar error+IRLS; fully PyTorch implementation arxiv.org/abs/2505.04612

FastMap: Revisiting Dense and Scalable Structure from Motion "FASTMAP, a redesigned SfM framework, achieves fast, high-accuracy dense structure from motion. On large scenes with thousands of images, FASTMAP is up to one to two orders of magnitude faster than GLOMAP and COLMAP.

FastMap: Revisiting Dense and Scalable Structure from Motion TL;DR: 2 orders of magnitude faster than GLOMAP; many GPU implementations; linear complexity for optimisation; comparable accuracy

Tired of teleoperating your robots? We built a way to scale robot datasets without teleop, dynamic simulation, or even robot hardware. Just one smartphone scan + one human hand demo video → thousands of diverse robot trajectories. Trainable by diffusion policy and VLA models

Interested in collecting robot training data without robots in the loop? 🦾 Check out this cool new approach that uses a single mobile device scan and a human demo video to generate diverse data for training diffusion and VLA manipulation policies. 🚀 Great work by Max Fu

Ever want to reconstruct and animate everyday articulated objects with no 3D scans or category priors? 🚀Introducing SplArt: Articulation Estimation & Part-Level Reconstruction with 3D Gaussian Splatting! #3Dvision #GaussianSplatting

#CVPR2025 next week will be an exciting one! Check out our work below on VLMs, VLAs, and 3D for robotics (including the first 3D VLMs for Robotics workshop)! Georgia Tech School of Interactive Computing Machine Learning at Georgia Tech

#CVPR2025 starts in two days, and can’t wait to share our new work! 🎉 We present ZeroGrasp, a unified framework for 3D reconstruction and grasp prediction that generalizes to unseen objects. Paper📄: arxiv.org/abs/2504.10857 Webpage🌐:sh8.io/#/zerograsp (1/4 🧵)

1X World Model Scaling Evaluation for Robots

How can we achieve both common sense understanding that can deal with varying levels of ambiguity in language and dextrous manipulation? Check out CodeDiffuser, a really neat work that bridges Code Gen with a 3D Diffusion Policy! This was a fun project with cool experiments! 🤖

We’re releasing the RoboArena today!🤖🦾 Fair & scalable evaluation is a major bottleneck for research on generalist policies. We’re hoping that RoboArena can help! We provide data, model code & sim evals for debugging! Submit your policies today and join the leaderboard! :) 🧵

Teleoperation is slow, expensive, and difficult to scale. So how can we train our robots instead? Introducing X-Sim: a real-to-sim-to-real framework that trains image-based policies 1) learned entirely in simulation 2) using rewards from human videos. portal-cornell.github.io/X-Sim

Great point! I think real2sim is a lucrative way to solve it — potential to scale better but many challenges still remain in getting it to work reliably in the real-world i.e. getting good sim vs real correlations or guarantees. Bonus point: Saves painstaking real-world evals in