Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Cameras
This addresses the challenge of enabling photorealistic mapping on portable devices for robotics applications, representing a strong specific gain rather than a foundational advancement.
The paper tackles the problem of resource-intensive neural rendering in SLAM systems by proposing Photo-SLAM, which uses hyper primitives to combine explicit geometric and implicit photometric features, resulting in a 30% higher PSNR and hundreds of times faster rendering speed on the Replica dataset while running in real-time on embedded platforms.
The integration of neural rendering and the SLAM system recently showed promising results in joint localization and photorealistic view reconstruction. However, existing methods, fully relying on implicit representations, are so resource-hungry that they cannot run on portable devices, which deviates from the original intention of SLAM. In this paper, we present Photo-SLAM, a novel SLAM framework with a hyper primitives map. Specifically, we simultaneously exploit explicit geometric features for localization and learn implicit photometric features to represent the texture information of the observed environment. In addition to actively densifying hyper primitives based on geometric features, we further introduce a Gaussian-Pyramid-based training method to progressively learn multi-level features, enhancing photorealistic mapping performance. The extensive experiments with monocular, stereo, and RGB-D datasets prove that our proposed system Photo-SLAM significantly outperforms current state-of-the-art SLAM systems for online photorealistic mapping, e.g., PSNR is 30% higher and rendering speed is hundreds of times faster in the Replica dataset. Moreover, the Photo-SLAM can run at real-time speed using an embedded platform such as Jetson AGX Orin, showing the potential of robotics applications.