Uncertainty modeling, grounded in 3D metric space, unlocks general-purpose state estimation. mac-vo.github.io MAC-VO outperforms SOTA methods and achieves reliable accuracy across platforms and datasets with no multi-frame optimization, loop closure, or fine-tuning! 👇🧵

🎭Recent work shows that models’ inductive biases for 'simpler' features may lead to shortcut learning. What do 'simple' vs 'complex' features look like? What roles do they play in generalization? Our new paper explores these questions. arxiv.org/pdf/2407.06076 #Neurips2024

Deeply honored to contribute one chapter with incredible teams for our SLAM Handbook. It has been an invaluable learning experience to collaborate with all the distinguished authors and I am truly grateful for their guidance. Appreciate for any suggestion to make book better!🎉

AI Software Engineering Agent using Deepseek R1 that can reason before writing code. It achieves similar performance as OpenAI o1 and Claude Sonnet 3.5 at a fraction of cost. 100% Opensource.

Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video Xiaohao Xu, Tianyi Zhang, Shibo, Xiang Li, Sibo Wang, Yongqi Chen, Ye Li, Bhiksha Raj, Matthew Johnson-Roberson, Sebastian Scherer, Xiaonan (Sean) Huang arxiv.org/abs/2501.14319

Acknowledge all the collaborator Jenny Geng Sebastian Scherer Can Xu Yutian Chen Shibo Our work is powered by Rerun Rerun for visualization, and Pypose for EKF integration PyPose Chen Wang.

We also release some LaTeX sty and bib files used in the handbook. If you are writing an ICRA paper on SLAM, these should be useful. Visit our GitHub repo for details: github.com/SLAM-Handbook-…

We have completed editing the SLAM Handbook "From Localization and Mapping to Spatial Intelligence" and released it. The 3-part handbook will be published by Cambridge University Press. Enjoy reading online for now!

GaussGym looks amazing!

If you have an Apple Vision Pro, try the Alive app to see nature in your own room. It was built by Jack during his individual project at Imperial Imperial Computing and is now available on the App Store.