Point cloud completion via structured feature maps using a feedback network

Abstract

In this paper, we tackle the challenging problem of point cloud completion from the perspective of feature learning. Our key observation is that to recover the underlying structures as well as surface details, given partial input, a fundamental component is a good feature representation that can capture both global structure and local geometric details. We accordingly first propose FSNet, a feature structuring module that can adaptively aggregate point-wise features into a 2D structured feature map by learning multiple latent patterns from local regions. We then integrate FSNet into a coarse-to-fine pipeline for point cloud completion. Specifically, a 2D convolutional neural network is adopted to decode feature maps from FSNet into a coarse and complete point cloud. Next, a point cloud upsampling network is used to generate a dense point cloud from the partial input and the coarse intermediate output. To efficiently exploit local structures and enhance point distribution uniformity, we propose IFNet, a point upsampling module with a self-correction mechanism that can progressively refine details of the generated dense point cloud. We have conducted qualitative and quantitative experiments on ShapeNet, MVP, and KITTI datasets, which demonstrate that our method outperforms state-of-the-art point cloud completion approaches.

CPDC-MFNet: conditional point diffusion completion network with Muti-scale Feedback Refine for 3D Terracotta Warriors

“…The feedback mechanism has been widely employed in various 2D image vision tasks, some works [28][29][30] use feedback mechanism in image super-resolution, Sam 31 and Feng 32 use it to enrich network features, and Chen 33 use it in image deraining problems. In the 3D field, Su 34 and Yan 35 use it to complete the point cloud. In our work, we use a feedback mechanism to refine our generation and accelerate the generation speed.…”