Messy Rooms Dataset

NIAID Data Ecosystem2026-05-01 收录

3D物体实例分割

室内场景理解

数据链接：

https://figshare.com/articles/dataset/Messy_Rooms_Dataset/23098790 数据链接链接失效反馈

官方服务：

资源简介：

Messy Rooms Dataset proposed in "Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion".

创建时间：

2023-09-30

Matterport3D

室内场景理解

计算机视觉

Matterport3D是由普林斯顿大学、斯坦福大学和慕尼黑工业大学联合创建的大规模室内RGB-D数据集，旨在为室内场景理解提供高质量数据支持。该数据集包含90个建筑规模场景的194,400张RGB-D图像，覆盖10,800个全景视图，提供表面重建、相机姿态以及二维和三维语义分割标注。数据采集自真实家庭环境，通过Matterport相机以360°全景方式获取，具备精确的全局对齐和多样化的视角采样。

github2017-09-18 更新2770

Dense prediction dataset

密度预测

室内场景理解

The NYUD V2 data set is comprised of video sequences from a variety of indoor scenes as recorded by both the RGB and Depth cameras from the Microsoft Kinect. It features: 1449 densely l

IEEE80

360D

全景深度估计

室内场景理解

A dataset of omnidirectional (360 - spherical panoramas) images with their corresponding ground truth depths. The 360 dataset provides 360 color images of indoor scenes along with

Zenodo2020-09-20 更新50

Hypersim Dataset

室内场景理解

计算机视觉

For many fundamental scene understanding tasks, it is difficult or impossible to obtain per-pixel ground truth labels from real images. Hypersim is a photorealistic synthetic dataset for holistic indo

paperswithcode.com140

HPDmobile H5 Image Zone Labels

人员存在检测

室内场景理解

Contains files for each hub and day with binary zone based occupancy, indicating if a human is present in the image (1) or not (0). These were automatically generated with the yoloV5 object detection

Figshare2021-10-21 更新50

Messy Rooms Dataset

资源简介：

相关数据集