344 datasets found

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

The dataset used in the paper is a 2D and 3D urban environment.

The Total Variation (TV) regularization is a deterministic technique that safeguards discontinuities in image processing tasks.

Wi-Mesh is a WiFi vision-based 3D human mesh construction system that leverages WiFi to visualize the shape and deformations of the human body for 3D mesh construction.

A comprehensive dataset featuring ten distinct hen breeds, capturing unique characteristics and traits of each breed.

Three datasets for phase recognition, pupil segmentation, and lens segmentation that are publicly released to support reproducibility and allow further investigations for lens...

ShapeNetV2 is a large-scale dataset of 3D shapes, with over 16,000 models, each described by a set of 3D coordinates.

The Image Matching Challenge dataset is a benchmark dataset for image matching and feature extraction.

The dataset is used for learning color constancy.

The dataset is used for auto-white balance correction.

Auto-white balance (AWB) correction is a critical operation in image signal processors for accurate and consistent color correction across various illumination scenarios.

The dataset used in the paper is not explicitly mentioned, but it is implied that it is a collection of images and videos of a kitchen scene.

The dataset used for training and evaluation of the proposed framework for unsupervised metric relocalization.

A data basis of irregularly sampled images on a sphere is provided in [4]. It is constructed by projecting the MNIST image digits on d = 4096 points randomly sampled on the 3D...

A dataset for cross-view image geo-localization with unknown orientation.

A dataset for predicting ground-level scene layout from aerial imagery.

A dataset for multi-view stereo reconstruction.

A dataset for 3D object reconstruction from a single image.

A crowd counting dataset with over 1000 labeled videos captured by over 100 monitoring cameras.

3D modelleme programları ile tasarlanan robotik kol sistemi, Raspberry Pi ve USB kamera kullanılarak bilgisayar görme uygulaması gerçekleştirilmiştir.