42 datasets found

MME: A comprehensive evaluation benchmark for multimodal large language models

Pyramid scene parsing network for semantic segmentation.

The SUN2012 dataset is a challenging dataset for object detection, with large cluttered scenes and small objects.

The dataset used in the paper is Places, a large dataset of 400k pairs of images from the Places 205 dataset and corresponding spoken audio captions.

ScanNetv2, ScanNet200, and Replica datasets for 3D instance segmentation

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

Indoor segmentation and support inference from RGB-D images.

The SUN RGB-D dataset includes 10335 RGB-D captures. The dataset was captured from different RGB-D sensors including Asus Xtion, RealSense, Kinect v1 and Kinect v2. Following...

Shapenet is a large-scale synthesis 3D object dataset, where we follow [9] to use the official test splits of chair, car, and motorbike categories for evaluation since they...

A large-scale hierarchical multi-view RGB-D object dataset.

A large-scale 3D database of object instances for scene understanding.

Neural Radiance Fields (NeRFs) model a 3D scene as a volumetric function, which can be rendered from arbitrary viewpoints to generate highly-realistic images.

The Replica dataset contains 18 various highly photo-realistic indoor environments. It provides dense-mesh, high-resolution RGBD images and a large range of instance annotations...

The Objaverse dataset contains around 800k 3D objects. After adopting simple filter leveraging CLIP [27] to remove the objects whose rendered images are not relevant to its...

A dataset for 3D object detection from LiDAR point clouds, containing 5,000 training frames and 3,000 validation frames.

The NYUDv2 dataset contains 1,449 labeled indoor-scene RGB images with both parsing annotations and Kinect depths.

RGB-D scene recognition approaches often train two standalone backbones for RGB and depth modalities with the same Places or ImageNet pre-training. However, the pre-trained...

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.

The dataset used for training and validation of the proposed approach to combine semantic segmentation and dense outlier detection.

The Cityscapes dataset is a large and famous city street scene semantic segmentation dataset. 19 classes of which 30 classes of this dataset are considered for training and...