Temporal Point Cloud Completion With Pose Disturbance

Point clouds collected by real-world sensors are always unaligned and sparse, which makes it hard to reconstruct the complete shape of object from a single frame data. In this work, we manage provide point sparse input with pose disturbance limited translation rotation. We also use temporal information enhance completion model, refining output sequence inputs. With help gated recovery units(GRU) attention mechanisms as units, propose cloud framework that accepts inputs, outputs consistent aligned clouds. Our network performs in an online manner presents refined for each frame, enables be integrated into any SLAM or reconstruction pipeline. As far know, our is first utilize ensure consistency transformation. Through experiments ShapeNet KITTI, prove effective both synthetic datasets.