Orbeez-SLAM: A Real-time Monocular Visual SLAM with ORB Features and NeRF-realized Mapping
This work addresses the need for spatial AI systems that can perform complex tasks through visual signals and cooperate with humans, offering a widely applicable solution for real-world scenarios.
The paper tackles the problem of creating a real-time monocular visual SLAM system that adapts to new scenes without pre-training and generates dense maps, achieving up to 800x faster performance than a strong baseline with superior rendering outcomes.
A spatial AI that can perform complex tasks through visual signals and cooperate with humans is highly anticipated. To achieve this, we need a visual SLAM that easily adapts to new scenes without pre-training and generates dense maps for downstream tasks in real-time. None of the previous learning-based and non-learning-based visual SLAMs satisfy all needs due to the intrinsic limitations of their components. In this work, we develop a visual SLAM named Orbeez-SLAM, which successfully collaborates with implicit neural representation and visual odometry to achieve our goals. Moreover, Orbeez-SLAM can work with the monocular camera since it only needs RGB inputs, making it widely applicable to the real world. Results show that our SLAM is up to 800x faster than the strong baseline with superior rendering outcomes. Code link: https://github.com/MarvinChung/Orbeez-SLAM.