python场景重建_ScanNet 室内场景3D重建丰富标记数据集

最新推荐文章于 2024-09-13 22:39:35 发布

weixin_39963523

最新推荐文章于 2024-09-13 22:39:35 发布

阅读量611

点赞数

文章标签： python场景重建

本文链接：https://blog.csdn.net/weixin_39963523/article/details/111749668

版权

ScanNet是一个包含250万帧的RGB-D视频数据集，涵盖1500多个扫描，附带3D相机位置、表面重建和实例级语义分割注释。数据组织按RGB-D序列，包括高质重建网格、清理和减少的网格等，可用于室内场景的3D重建研究。

摘要由CSDN通过智能技术生成

ScanNet

ScanNet is an RGB-D video dataset containing 2.5 million views in more than 1500 scans, annotated with 3D camera poses, surface reconstructions, and instance-level semantic segmentations.

ScanNet Data

If you would like to download the ScanNet data, please fill out an agreement to the ScanNet Terms of Use and send it to us at scannet@googlegroups.com.

If you have not received a response within a week, it is likely that your email is bouncing - please check this before sending repeat requests.

Please check the changelog for updates to the data release.

Data Organization

The data in ScanNet is organized by RGB-D sequence. Each sequence is stored under a directory with named scene_, or scene%04d_%02d, where each space corresponds to a unique location (0-indexed). The raw data captured during scanning, camera poses and surface mesh reconstructions, and annotation metadata are all stored together for the given sequence. The directory has the following structure:

|-- .sens

RGB-D sensor stream containing color frames, depth frames, camera poses and other data

|-- _vh_clean.ply

High quality reconstructed mesh

|-- _vh_clean_2.ply

Cleaned and decimated mesh for semantic annotations

|-- _vh_clean_2.0.010000.segs.json

Over-segmentation of annotation mesh

|-- .aggregation.json, _vh_clean.aggregation.json

Aggregated instance-level semantic annotations on lo-res, hi-res meshes, respectively

|-- _vh_clean_2.0.010000.segs.json, _vh_