paper-with-me

Papers

Associatively Segmenting Instances and Semantics in Point Clouds

2019-02-26 · CVPR 2019 6 · Xinlong Wang, Shu Liu, Xiaoyong Shen, Chunhua Shen, Jiaya Jia

A 3D point cloud describes the real scene precisely and intuitively.To date how to segment diversified elements in such an informative 3D scene is rarely discussed. In this paper, we first introduce a simple and flexible framework to segment instances and semantics in point clouds simultaneously. Then, we propose two approaches which make the two tasks take advantage of each other, leading to a win-win situation. Specifically, we make instance segmentation benefit from semantic segmentation through learning semantic-aware point-level instance embedding. Meanwhile, semantic features of the points belonging to the same instance are fused together to make more accurate per-point semantic predictions. Our method largely outperforms the state-of-the-art method in 3D instance segmentation along with a significant improvement in 3D semantic segmentation. Code has been made available at: https://github.com/WXinlong/ASIS.

📄 PDF Abstract BibTeX arXiv:1902.09852

Code (3)

WXinlong/ASIS 공식 구현 tf
LebronGG/ASIS tf
tuananh1007/Associatively-Segmenting-Instances-and-Semantics-in-Point-Clouds tf

Tasks

3D Instance Segmentation3D Semantic SegmentationInstance SegmentationSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Enriching thermal point clouds of buildings using semantic 3D building models

2024-07-31 · Jingwei Zhu, Olaf Wysocki, Christoph Holst, Thomas H. Kolbe

Thermal point clouds integrate thermal radiation and laser point clouds effectively. However, the semantic information for the interpretation of building thermal point clouds can hardly be precisely inferred. Transferrin…

Position

A Pipeline for Segmenting and Structuring RGB-D Data for Robotics Applications

2024-10-23 · Zhiwu Zheng, Lauren Mentzer, Berk Iskender, Michael Price 외

We introduce a novel pipeline for segmenting and structuring color and depth (RGB-D) data. Existing processing pipelines for RGB-D data have focused on extracting geometric information alone. This approach precludes the …

Identifying Unknown Instances for Autonomous Driving

2019-10-24 · Kelvin Wong, Shenlong Wang, Mengye Ren, Ming Liang 외

In the past few years, we have seen great progress in perception algorithms, particular through the use of deep learning. However, most existing approaches focus on a few categories of interest, which represent only a sm…

Autonomous DrivingInstance SegmentationSemantic Segmentation

3D Segmentation of Humans in Point Clouds with Synthetic Data

2022-12-01 · ICCV 2023 1 · Ayça Takmaz, Jonas Schult, Irem Kaftan, Mertcan Akçay 외

Segmenting humans in 3D indoor scenes has become increasingly important with the rise of human-centered robotics and AR/VR applications. To this end, we propose the task of joint 3D human semantic segmentation, instance …

Instance SegmentationSegmentationSemantic SegmentationSynthetic Data Generation

Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision

2022-01-09 · Yan Liu, Qingyong Hu, Yinjie Lei, Kai Xu 외

Learning dense point-wise semantics from unstructured 3D point clouds with fewer labels, although a realistic problem, has been under-explored in literature. While existing weakly supervised methods can effectively learn…

Semantic Segmentation