3D Dynamic Point Cloud Inpainting via Temporal Consistency on Graphs
This addresses missing data in 3D dynamic point clouds for applications like tele-presence and gaming, but it is incremental as it builds on existing graph signal processing tools.
The paper tackles the problem of holes in 3D dynamic point clouds caused by motion and acquisition limits by proposing an inpainting method that uses intra-frame self-similarity and inter-frame consistency, resulting in significant outperformance over three competing methods in objective and subjective quality.
With the development of 3D laser scanning techniques and depth sensors, 3D dynamic point clouds have attracted increasing attention as a representation of 3D objects in motion, enabling various applications such as 3D immersive tele-presence, gaming and navigation. However, dynamic point clouds usually exhibit holes of missing data, mainly due to the fast motion, the limitation of acquisition and complicated structure. Leveraging on graph signal processing tools, we represent irregular point clouds on graphs and propose a novel inpainting method exploiting both intra-frame self-similarity and inter-frame consistency in 3D dynamic point clouds. Specifically, for each missing region in every frame of the point cloud sequence, we search for its self-similar regions in the current frame and corresponding ones in adjacent frames as references. Then we formulate dynamic point cloud inpainting as an optimization problem based on the two types of references, which is regularized by a graph-signal smoothness prior. Experimental results show the proposed approach outperforms three competing methods significantly, both in objective and subjective quality.