From the 2 of 4 linked papers with an AI index.
4 papers
MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos
Ziren Gong, Xiaohan Li, Fabio Tosi +4
The paper introduces MAGiSt3R, a multi-agent framework that reconstructs 3D scenes and tracks camera pose from monocular RGB videos in near real-time using feed-forward models and…
DINO-SLAM: DINO-informed RGB-D SLAM for Neural Implicit and Explicit Representations
Ziren Gong, Xiaohan Li, Fabio Tosi +4
The paper introduces DINO-SLAM, a system that combines DINO semantic features with a geometry encoder to improve both neural implicit (NeRF) and explicit (Gaussian Splatting) SLAM…
Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videos
Ziren Gong, Xiaohan Li, Fabio Tosi +4
We present Ov3R, a novel framework for open-vocabulary semantic 3D reconstruction from RGB video streams, designed to advance Spatial AI. The system features two key components: CL…
Stereo 3D Gaussian Splatting SLAM for Outdoor Urban Scenes
Xiaohan Li, Ziren Gong, Fabio Tosi +4
3D Gaussian Splatting (3DGS) has recently gained popularity in SLAM applications due to its fast rendering and high-fidelity representation. However, existing 3DGS-SLAM systems hav…