Topology-Change-Aware Volumetric Fusion for Dynamic Scene Reconstruction
This addresses a challenging issue in dynamic scene reconstruction for applications like robotics or VR, though it appears incremental as it builds on an existing framework.
The paper tackles the problem of 4D reconstruction of dynamic scenes under topology changes by redesigning the classic volumetric fusion framework, introducing a Non-manifold Volumetric Grid to allow connectivity updates, resulting in convincing reconstruction results compared to state-of-the-art methods.
Topology change is a challenging problem for 4D reconstruction of dynamic scenes. In the classic volumetric fusion-based framework, a mesh is usually extracted from the TSDF volume as the canonical surface representation to help estimating deformation field. However, the surface and Embedded Deformation Graph (EDG) representations bring conflicts under topology changes since the surface mesh has fixed-connectivity but the deformation field can be discontinuous. In this paper, the classic framework is re-designed to enable 4D reconstruction of dynamic scene under topology changes, by introducing a novel structure of Non-manifold Volumetric Grid to the re-design of both TSDF and EDG, which allows connectivity updates by cell splitting and replication. Experiments show convincing reconstruction results for dynamic scenes of topology changes, as compared to the state-of-the-art methods.