1,082 datasets found

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

RGB-D images dataset for indoor segmentation and support inference.

Depth map super-resolution (DMSR) is a practical and valuable computer vision task. DMSR requires upscaling a low-resolution (LR) depth map into a high-resolution (HR) space.

The dataset used for evaluating latent-space interpolation algorithms for variational autoencoders.

The PASCAL Visual Object Classes Challenge (VOC) is a benchmark dataset for object detection and semantic segmentation.

A dataset for metrical reconstruction of human faces.

A dataset for capturing 3D faces using polarized spherical gradient illumination.

A 3D morphable model of craniofacial shape and texture variation.

A diffusion-based 3D facial generative model conditioned on identity embeddings.

Conformer is a dual network structure that combines CNN-based local features with transformer-based global representations for enhanced representation learning.

Scannet: Richly-annotated 3D reconstructions of indoor scenes.

The Google Scanned Objects dataset is a collection of over one thousand 3D-scanned household items. The dataset is used for evaluation of the proposed ConsistNet model.

HICO-Det is a benchmark for Human-Object Interaction (HOI) detection.

Human-Object Interaction (HOI) detection is a significant task to make a machine understand human activities in a static image at a fine-grained level.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used four widely used datasets: CIFAR10, CIFAR100, SVHN, and ImageNet.

Local processing is an essential feature of CNNs and other neural network architectures—it is one of the reasons why they work so well on images where relevant information is,...

The DRIVE dataset includes 40 color fundus photographs divided into two parts: 20 training images and 20 test images with manual segmentation of the vessels and binary masks of...

Graph convolutional neural network (GCN) has effectively boosted the multi-label image recognition task by introducing label dependencies based on statistical label...

Aerial images of London.

Street View images of London.