Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion

By Xu Yan, Jiantao Gao, Jie Li, Ruimao Zhang, Zhen Li, Rui Huang, Shuguang Cui. AAAI Conference on Artificial Intelligence, 2020

383 citations recorded by the source corpus.

LiDAR point cloud analysis is a core task for 3D computer vision, especially for autonomous driving. However, due to the severe sparsity and noise interference in the single sweep LiDAR point cloud, the accurate semantic segmentation is non-trivial to achieve. In this paper, we propose a novel sparse LiDAR point cloud semantic segmentation framework assisted by learned contextual shape priors. In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input. By merging multiple frames in the LiDAR sequence as supervision, the optimized SSC module has learned the contextual shape priors from sequential LiDAR data, completing the sparse single sweep point cloud to the dense one. Thus, it inherently improves SS optimization through fully end-to-end training. Besides, a Point-Voxel Interaction (PVI) module is proposed to further enhance the knowledge fusion between SS and SSC tasks, i.e., promoting the interaction of incomplete local geometry of point cloud and complete voxel-wise global structure. Furthermore, the auxiliary SSC and PVI modules can be discarded during inference without extra burden for SS. Extensive experiments confirm that our JS3C-Net achieves superior performance on both SemanticKITTI and SemanticPOSS benchmarks, i.e., 4% and 3% improvement correspondingly.

Subfields: Aerospace Engineering, Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/601ad774f6305f8a78e878665b3623f2239687c5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Yunpeng Zhang
2. Zhengbiao Zhu
3. Chaoda Zheng
4. Jiwen Lu
5. Xu Yan
6. Dalong Du
7. Jie Zhou
8. Shiv Ram Dubey

In Computational Mechanics

1. Zhengbiao Zhu
2. Dalong Du
3. Yunpeng Zhang
4. Chaoda Zheng
5. Jiwen Lu
6. Xu Yan
7. Zhen Li
8. Ruimao Zhang

In Computer Vision and Pattern Recognition

1. Jie Zhou
2. Jiwen Lu
3. Zhengbiao Zhu
4. Dalong Du
5. Yunpeng Zhang
6. Chaoda Zheng
7. Shenghui Cui
8. Xu Yan

Citations in the corpus

• Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving (2023, neutral): “Another related task is Semantic Scene Completion (SSC) [1, 6, 9, 3, 24, 50, 38, 49, 7, 19, 50, 32, 20, 29, 54], whose goal is to estimate a dense semantic space from partial observations.”
• OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction (2023, methodology): “For the driving scenes, most existing methods [43, 11, 8, 25, 50] still rely on the expensive Li-DAR sensors for explicit depth measurements.”
• 2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds (2022, background): “In the past few years, the research community has devoted significant effort to understanding natural scenes using either camera images [4–7] or LiDAR point clouds [2, 8–12] as the input.”
• Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction (2023, background): “The ability to describe fine-grained 3D structures makes voxel-based representation favorable for 3D semantic occupancy prediction tasks including lidar segmentation [12, 29, 40, 44, 45, 51] and 3D scene completion [5, 10, 23, 38, 43].”