Knowledge Commons of Institute of Automation,CAS
Efficient 3D Scene Semantic Segmentation via Active Learning on Rendered 2D Images | |
Mengqi Rong1,2,3; Hainan Cui1,2,3; Shuhan Shen1,2,3 | |
发表期刊 | IEEE Transactions on Image Processing |
2023-06-20 | |
卷号 | 32页码:3521-3535 |
文章类型 | 期刊论文 |
摘要 | Inspired by Active Learning and 2D-3D semantic fusion, we proposed a novel framework for 3D scene semantic segmentation based on rendered 2D images, which could efficiently achieve semantic segmentation of any large-scale 3D scene with only a few 2D image annotations. In our framework, we first render perspective images at certain positions in the 3D scene. Then we continuously fine-tune a pre-trained network for image semantic segmentation and project all dense predictions to the 3D model for fusion. In each iteration, we evaluate the 3D semantic model and re-render images in several representative areas where the 3D segmentation is not stable and send them to the network for training after annotation. Through this iterative process of rendering-segmentation-fusion, it can effectively generate difficult-to-segment image samples in the scene, while avoiding complex 3D annotations, so as to achieve label-efficient 3D scene segmentation. Experiments on three large-scale indoor and outdoor 3D datasets demonstrate the effectiveness of the proposed method compared with other state-of-the-art. |
收录类别 | SCI |
WOS记录号 | WOS:001022071600001 |
七大方向——子方向分类 | 三维视觉 |
国重实验室规划方向分类 | 环境多维感知 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/52435 |
专题 | 中科院工业视觉智能装备工程实验室_精密感知与控制 |
通讯作者 | Shuhan Shen |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences, Beijing, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China 3.CASIA-SenseTime Research Group, Beijing, China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Mengqi Rong,Hainan Cui,Shuhan Shen. Efficient 3D Scene Semantic Segmentation via Active Learning on Rendered 2D Images[J]. IEEE Transactions on Image Processing,2023,32:3521-3535. |
APA | Mengqi Rong,Hainan Cui,&Shuhan Shen.(2023).Efficient 3D Scene Semantic Segmentation via Active Learning on Rendered 2D Images.IEEE Transactions on Image Processing,32,3521-3535. |
MLA | Mengqi Rong,et al."Efficient 3D Scene Semantic Segmentation via Active Learning on Rendered 2D Images".IEEE Transactions on Image Processing 32(2023):3521-3535. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Efficient_3D_Scene_S(6587KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论