SplitFusion: Simultaneous Tracking and Mapping for Non-Rigid Scenes
This addresses the challenge of dynamic scene reconstruction in robotics and AR/VR, though it appears incremental by combining existing techniques like semantic segmentation and ICP.
The paper tackles the problem of simultaneous tracking and mapping in scenes with both rigid and non-rigid components, achieving accurate environment maps and well-reconstructed non-rigid targets like moving humans.
We present SplitFusion, a novel dense RGB-D SLAM framework that simultaneously performs tracking and dense reconstruction for both rigid and non-rigid components of the scene. SplitFusion first adopts deep learning based semantic instant segmentation technique to split the scene into rigid or non-rigid surfaces. The split surfaces are independently tracked via rigid or non-rigid ICP and reconstructed through incremental depth map fusion. Experimental results show that the proposed approach can provide not only accurate environment maps but also well-reconstructed non-rigid targets, e.g. the moving humans.