Point Cloud Instance Segmentation using Probabilistic Embeddings
In this paper we propose a new framework for point cloud instance segmentation. Our framework has two steps: an embedding step and a clustering step. In the embedding step, our main contribution is to propose a probabilistic embedding space for point cloud embedding. Specifically, each point is represented as a tri-variate normal distribution. In the clustering step, we propose a novel loss function, which benefits both the semantic segmentation and the clustering. Our experimental results show important improvements to the SOTA, i.e., 3.1% increased average per-category mAP on the PartNet dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Instance SegmentationClusteringInstance SegmentationSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
In this paper, we propose a novel joint instance and semantic segmentation approach, which is called JSNet, in order to address the instance and semantic segmentation of 3D point clouds simultaneously. Firstly, we build …
3D Instance SegmentationClusteringInstance SegmentationSegmentation+13D Graph Embedding Learning with a Structure-aware Loss Function for Point Cloud Semantic Instance Segmentation
This paper introduces a novel approach for 3D semantic instance segmentation on point clouds. A 3D convolutional neural network called submanifold sparse convolutional network is used to generate semantic predictions and…
3D Instance Segmentation3D Semantic Instance SegmentationGraph EmbeddingInstance Segmentation+1Towards accurate instance segmentation in large-scale LiDAR point clouds
Panoptic segmentation is the combination of semantic and instance segmentation: assign the points in a 3D point cloud to semantic categories and partition them into distinct object instances. It has many obvious applicat…
ClusteringInstance SegmentationManagementObject+4PointTrack++ for Effective Online Multi-Object Tracking and Segmentation
Multiple-object tracking and segmentation (MOTS) is a novel computer vision task that aims to jointly perform multiple object tracking (MOT) and instance segmentation. In this work, we present PointTrack++, an effective …
Data AugmentationDecoderInstance SegmentationMulti-Object Tracking+7JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields
Deep learning techniques have become the to-go models for most vision-related tasks on 2D images. However, their power has not been fully realised on several tasks in 3D space, e.g., 3D scene understanding. In this work,…
3D Instance Segmentation3D Semantic Instance Segmentation3D Semantic SegmentationScene Understanding+1