Semi-supervised Implicit Scene Completion from Sparse LiDAR

29 Nov 2021  ·  Pengfei Li, Yongliang Shi, Tianyu Liu, Hao Zhao, Guyue Zhou, Ya-Qin Zhang ·

Recent advances show that semi-supervised implicit representation learning can be achieved through physical constraints like Eikonal equations. However, this scheme has not yet been successfully used for LiDAR point cloud data, due to its spatially varying sparsity. In this paper, we develop a novel formulation that conditions the semi-supervised implicit function on localized shape embeddings. It exploits the strong representation learning power of sparse convolutional networks to generate shape-aware dense feature volumes, while still allows semi-supervised signed distance function learning without knowing its exact values at free space. With extensive quantitative and qualitative results, we demonstrate intrinsic properties of this new learning system and its usefulness in real-world road scenes. Notably, we improve IoU from 26.3% to 51.0% on SemanticKITTI. Moreover, we explore two paradigms to integrate semantic label predictions, achieving implicit semantic completion. Code and models can be accessed at

PDF Abstract


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here