aiqbench analysis
This research introduces All-St3R SLAM, a real-time RGB framework that improves dynamic environment mapping by precisely masking moving pixels without relying on external segmentation models. By leveraging motion discrepancies between ego-motion predictions and point tracking, the system achieves approximately 10 FPS performance while avoiding the over-removal issues common in existing dense dynamic SLAM approaches. The method represents a significant practical advancement for autonomous systems operating in complex, non-static environments using only standard RGB inputs.
All-St3R SLAM: Real-time RGB Dynamic SLAM with Pixel-wise Motion Masking
arXiv:2610.16143v1 Announce Type: cross Abstract: SLAM (Simultaneous Localization and Mapping) is a core technology in autonomous systems that enables them to estimate their own position and build a map of unknown environments simultaneously. SLAM systems in dynamic environments are of great practical importance. However, existing dynamic SLAM approaches still have several limitations like over-removal and high computational costs. To address these limitations, we propose a real-time RGB Dynamic SLAM framework that precisely removes moving objects at the pixel level without relying on predefined labels or segmentation models. Our system combines pixel motion predicted by ego-motion using DUSt3R with point tracking from All-Tracker, removing only actually moving pixels by analyzing discrepancies between the two motion sources. Unlike object-level masking methods, our approach eliminates only currently moving regions, allowing temporarily static parts to be utilized for tracking. Operating at approximately 10 FPS, the system achieves real-time performance on standard 30 FPS video streams by subsampling every 3 frames. Relying solely on RGB inputs, this significantly improves upon state-of-the-art dense dynamic SLAM approaches (0.5-3 FPS), presenting a highly practical solution.
Abstract:SLAM (Simultaneous Localization and Mapping) is a core technology in autonomous systems that enables them to estimate their own position and build a map of unknown environments simultaneously. SLAM systems in dynamic environments are of great practical importance. However, existing dynamic SLAM approaches still have several limitations like over-removal and high computational costs. To address these limitations, we propose a real-time RGB Dynamic SLAM framework that precisely removes moving objects at the pixel level without relying on predefined labels or segmentation models. Our system combines pixel motion predicted by ego-motion using DUSt3R with point tracking from All-Tracker, removing only actually moving pixels by analyzing discrepancies between the two motion sources. Unlike object-level masking methods, our approach eliminates only currently moving regions, allowing temporarily static parts to be utilized for tracking. Operating at approximately 10 FPS, the system achieves real-time performance on standard 30 FPS video streams by subsampling every 3 frames. Relying solely on RGB inputs, this significantly improves upon state-of-the-art dense dynamic SLAM approaches (0.5-3 FPS), presenting a highly practical solution.
Accepted to the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2026. Project Page: this https URL
Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
arXiv:2610.16143 [cs.CV]
(or arXiv:2610.16143v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.16143 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 287 words
Related coverage
Noctif3R: Feed-Forward Monocular Real-Time SLAM for Photon-Limited Scenes on Embedded Hardware
arXiv · Sep 21, 2026
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · Sep 25, 2026
Game Design Creativity evals
LessWrong · Oct 12, 2026
NGD-SLAM: Towards Real-Time Dynamic SLAM without GPU
arXiv · Sep 1, 2026