22 datasets found

The KITTI-C dataset is a robustness benchmark for outdoor monocular depth estimation under data corruptions.

SCARED is one of the MICCAI 2019 challenges, and provided a training set acquired from 7 pigs. Each pig corresponds to 5 videos recorded by a binocular camera from 5 different...

The FlyingThings3D dataset is a benchmark for stereo matching, consisting of a large collection of images and corresponding disparity maps.

A weakly-supervised depth estimation network using attention mechanism for cases with wrong labels.

The dataset used for training the D2-Net model, consisting of 327,036 image pairs with at least 50% overlap in the sparse SfM point cloud.

The dataset for Symmetry-awareDepthEstimationusingDeepNeuralNetworks, containing product images with reflection symmetry.

Depth from focus (DFF) is a highly ill-posed inverse problem because the optimal focal distance is inferred from sharpness measures which fail in untextured areas. Existing...

The dataset is used for depth estimation from monocular images and sparse radar data.

The NYUv2 dataset is a large-scale dataset for 3D object recognition and semantic segmentation. It contains 206 test set video sequences with 135 classes.

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

DepthP+P: A method for self-supervised monocular depth estimation using planar and parallax.

MonoDiffusion: A novel self-supervised monocular depth estimation framework by reformulating it as an iterative denoising process.

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

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.

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 the KITTI Vision Benchmark and Cityscapes dataset for monocular depth estimation and structure prediction.

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 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...

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...