40 datasets found

OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas.

Depth estimation is a crucial step for 3D reconstruction with panorama images in recent years. Panorama images maintain the complete spatial information but introduce distortion...

The dataset used in this paper is an ICL-NUIM dataset, which contains images and depth maps.

The NYU-Depth V2 dataset contains pairs of RGB and depth images collected from Microsoft Kinect in 464 indoor scenes.

KeystoneDepth is a collection of over 10,000 rectified antique stereographs of historical scenes captured between 1860 and 1963.

A benchmark for stereo matching and depth estimation.

Monocular depth estimation is a fundamental knowledge for autonomous systems that need to assess their own state and perceive the surrounding environment.

The NYU Depth V2 dataset contains two sub-datasets: labeled dataset and raw dataset. The raw dataset consists of 249 training scenes and 215 test scenes captured with Microsoft...

KITTI 2012 is a real-world dataset in the outdoor scenario, and contains 194 training and 195 testing stereo image pairs with the size of 376 × 1240.

The ClearPose dataset consists of 63 objects arranged in numerous configurations.

The ClearPose Transparent Object Depth Completion dataset consists of 63 objects arranged in numerous configurations.

A reference model for depth estimation, used for evaluating the performance of the LDM3D model.

A dataset of images used for training and testing the DPT-Large depth estimation model.

Multi-task learning (MTL) research is broadly divided into two categories: one is to learn the correlation between tasks through model structures, and the other is to balance...

The dataset used in the paper is a spike dataset generated from RGB frames of four open access outdoor datasets, including Kitti, Driving Stereo, Driving Stereo Weather, and...

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 ScanNet dataset is a large-scale indoor dataset composed of monocular sequences with ground truth poses and depth images.

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...

Feature matching is a fundamental problem for many computer vision tasks, such as object recognition, structure from motion, and simultaneous localization and mapping.

The dataset used in the paper is the KITTI dataset, which is a benchmark for monocular depth estimation. The dataset consists of a large collection of images and corresponding...