Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning
Contextual Shape Priors from Scene Completion
- URL: http://arxiv.org/abs/2012.03762v1
- Date: Mon, 7 Dec 2020 14:58:25 GMT
- Title: Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning
Contextual Shape Priors from Scene Completion
- Authors: Xu Yan, Jiantao Gao, Jie Li, Ruimao Zhang, Zhen Li, Rui Huang,
Shuguang Cui
- Abstract summary: LiDAR point cloud analysis is a core task for 3D computer vision, especially for autonomous driving.
We propose a novel sparse LiDAR point cloud semantic segmentation framework assisted by learned contextual shape priors.
Our JS3C-Net achieves superior performance on both SemanticKITTI and SemanticPOSS benchmarks.
- Score: 43.86692068523167
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- FASTC: A Fast Attentional Framework for Semantic Traversability Classification Using Point Cloud [7.711666704468952]
We address the problem of traversability assessment using point clouds.
We propose a pillar feature extraction module that utilizes PointNet to capture features from point clouds organized in vertical volume.
We then propose a newtemporal attention module to fuse multi-frame information, which can properly handle the varying density problem of LIDAR point clouds.
arXiv Detail & Related papers (2024-06-24T12:01:55Z) - PointSSC: A Cooperative Vehicle-Infrastructure Point Cloud Benchmark for
Semantic Scene Completion [4.564209472726044]
Semantic Scene Completion aims to jointly generate space occupancies and semantic labels for complex 3D scenes.
PointSSC is the first cooperative vehicle-infrastructure point cloud benchmark for semantic scene completion.
arXiv Detail & Related papers (2023-09-22T08:39:16Z) - LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and
Semantic-Aware Alignment [63.83894701779067]
We propose LCPS, the first LiDAR-Camera Panoptic network.
In our approach, we conduct LiDAR-Camera fusion in three stages.
Our fusion strategy improves about 6.9% PQ performance over the LiDAR-only baseline on NuScenes dataset.
arXiv Detail & Related papers (2023-08-03T10:57:58Z) - Clustering based Point Cloud Representation Learning for 3D Analysis [80.88995099442374]
We propose a clustering based supervised learning scheme for point cloud analysis.
Unlike current de-facto, scene-wise training paradigm, our algorithm conducts within-class clustering on the point embedding space.
Our algorithm shows notable improvements on famous point cloud segmentation datasets.
arXiv Detail & Related papers (2023-07-27T03:42:12Z) - LiDAR-based 4D Panoptic Segmentation via Dynamic Shifting Network [56.71765153629892]
We propose the Dynamic Shifting Network (DS-Net), which serves as an effective panoptic segmentation framework in the point cloud realm.
Our proposed DS-Net achieves superior accuracies over current state-of-the-art methods in both tasks.
We extend DS-Net to 4D panoptic LiDAR segmentation by the temporally unified instance clustering on aligned LiDAR frames.
arXiv Detail & Related papers (2022-03-14T15:25:42Z) - SCSS-Net: Superpoint Constrained Semi-supervised Segmentation Network
for 3D Indoor Scenes [6.3364439467281315]
We propose a superpoint constrained semi-supervised segmentation network for 3D point clouds, named as SCSS-Net.
Specifically, we use the pseudo labels predicted from unlabeled point clouds for self-training, and the superpoints produced by geometry-based and color-based Region Growing algorithms are combined to modify and delete pseudo labels with low confidence.
arXiv Detail & Related papers (2021-07-08T04:43:21Z) - SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine
Reconstruction with Self-Projection Optimization [52.20602782690776]
It is expensive and tedious to obtain large scale paired sparse-canned point sets for training from real scanned sparse data.
We propose a self-supervised point cloud upsampling network, named SPU-Net, to capture the inherent upsampling patterns of points lying on the underlying object surface.
We conduct various experiments on both synthetic and real-scanned datasets, and the results demonstrate that we achieve comparable performance to the state-of-the-art supervised methods.
arXiv Detail & Related papers (2020-12-08T14:14:09Z) - LiDAR-based Panoptic Segmentation via Dynamic Shifting Network [56.71765153629892]
LiDAR-based panoptic segmentation aims to parse both objects and scenes in a unified manner.
We propose the Dynamic Shifting Network (DS-Net), which serves as an effective panoptic segmentation framework in the point cloud realm.
Our proposed DS-Net achieves superior accuracies over current state-of-the-art methods.
arXiv Detail & Related papers (2020-11-24T08:44:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.