13 datasets found

The dataset used in the paper is the LEMO dataset.

The dataset used in the paper is the MultiDex dataset.

3D semantic parsing of large-scale indoor spaces.

The SUNRGB-D dataset features 5,285 training and 5,050 test samples from multiple RGB-D cameras. The dataset provides annotations for the first 37 NYUv2 semantic classes and for...

Street View is a large-scale dataset of 3D scenes, consisting of millions of images taken from street-level cameras.

A large-scale dataset of multi-view images for 3D scene understanding.

The LERF dataset is a dataset for 3D scene understanding, where the goal is to reconstruct and segment 3D scenes. The dataset is constructed by capturing 360-degree views of 9...

The LERF-Mask dataset is a dataset for open-vocabulary 3D segmentation, where the goal is to segment anything in a 3D scene. The dataset is constructed by annotating three...

The dataset used in the paper is ScanNetV2, a real-world dataset for indoor scenes. It contains 1205 training scenes and 312 testing scenes, with instance-level object bounding...

Learning from bounding-boxes annotations has shown great potential in weakly-supervised 3D point cloud instance segmentation. However, we observed that existing methods would...

The dataset used for training and testing the proposed RGBD-based obstacle avoidance system for visually impaired people.

The Make3D dataset is a small but challenging dataset for 3D object recognition and scene understanding, which consists of 134 images with aligned depth information.

The dataset used in the paper is a real-world 3D point cloud dataset, which is used for 3D shape classification, part segmentation, and shape retrieval tasks.