260 datasets found

Intrinsic Images in the Wild (IIW) dataset for intrinsic image decomposition.

A custom physically rendered dataset for intrinsic image decomposition of indoor scenes.

Fine-grained object recognition in remote sensing images is a challenging task. Objects have few texture features at high viewing distances, and thus it is hard to identify them.

The dataset used for training and testing the conditional generative adversarial networks for image enhancement.

The dataset used for training and testing the conditional generative adversarial networks for occluded object reconstruction.

Weakly-supervised segmentation (WSS) methods, reliant on image-level lack of explicit correspondence between labels and regions of interest (ROIs), posing a significant challenge.

Weakly-supervised segmentation (WSS) methods, reliant on image-level lack of explicit correspondence between labels and regions of interest (ROIs), posing a significant challenge.

MOS600 is a benchmark testing set for Meticulous Object Segmentation (MOS). It contains 600 high resolution images with complex boundaries.

Two large publicly-available datasets for building segmentation: Inria and DeepGlobe (termed DG)

The dataset used in the paper is a collection of images, and the authors used it to evaluate the performance of their constrained spectral clustering algorithm.

The LITS MICCAI-2017 challenge dataset is used for training and testing the proposed 2-stage cascaded model for segmentation of liver and its tumors in CT images.

The Taskonomy dataset contains 16 types of annotation, including object classification, scene classification, depth estimation, surface normals, curvature estimation, edge...

Image quality is the basis of image communication and understanding tasks. Due to the blur and noise effects caused by imaging, transmission and other processes, the image...

The dataset is used for community detection in complex physical systems, including image segmentation and analysis of amorphous materials.

Aerial images and building footprints from GIS resources

Tomatopia is a new, large-scale dataset of greenhouse tomatoes, manually annotated in a pixel-wise manner. The dataset comprises high-resolution RGB-D images and pixel-level...

The dataset used in this paper for psoas muscle segmentation in low-dose X-ray computed tomography images.

A python package consisting of some well-known loss functions widely used for image segmentation.

MS Lesion Segmentation: Revisiting Weighting Mechanisms for Federated Learning

The UAVid dataset is used for evaluating the proposed method.