CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusion

TL;DR

CasFusionNet is a novel cascaded point cloud network that effectively combines scene completion and semantic segmentation through dense feature fusion, outperforming existing voxel-based and point-based methods.

Contribution

The paper introduces a new cascaded network architecture with dense feature fusion for simultaneous scene completion and semantic segmentation of point clouds.

Findings

Outperforms state-of-the-art methods in scene completion

Achieves superior semantic segmentation accuracy

Demonstrates effectiveness on two point-based datasets

Abstract

Semantic scene completion (SSC) aims to complete a partial 3D scene and predict its semantics simultaneously. Most existing works adopt the voxel representations, thus suffering from the growth of memory and computation cost as the voxel resolution increases. Though a few works attempt to solve SSC from the perspective of 3D point clouds, they have not fully exploited the correlation and complementarity between the two tasks of scene completion and semantic segmentation. In our work, we present CasFusionNet, a novel cascaded network for point cloud semantic scene completion by dense feature fusion. Specifically, we design (i) a global completion module (GCM) to produce an upsampled and completed but coarse point set, (ii) a semantic segmentation module (SSM) to predict the per-point semantic labels of the completed points generated by GCM, and (iii) a local refinement module (LRM) to further refine the coarse completed points and the associated labels from a local perspective. We organize the above three modules via dense feature fusion in each level, and cascade a total of four levels, where we also employ feature fusion between each level for sufficient information usage. Both quantitative and qualitative results on our compiled two point-based datasets validate the effectiveness and superiority of our CasFusionNet compared to state-of-the-art methods in terms of both scene completion and semantic segmentation. The codes and datasets are available at: https://github.com/JinfengX/CasFusionNet.