Cityscapes is a large-scale database which focuses on semantic understanding of urban street scenes. It provides semantic, instance-wise, and dense pixel annotations for 30 classes grouped into 8 categories (flat surfaces, humans, vehicles, constructions, objects, nature, sky, and void). The dataset consists of around 5000 fine annotated images and 20000 coarse annotated ones. Data was captured in 50 cities during several months, daytimes, and good weather conditions. It was originally recorded as video so the frames were manually selected to have the following features: large number of dynamic objects, varying scene layout, and varying background.
3,323 PAPERS • 54 BENCHMARKS
Berkeley Segmentation Data Set 500 (BSDS500) is a standard benchmark for contour detection. This dataset is designed for evaluating natural edge detection that includes not only object contours but also object interior boundaries and background boundaries. It includes 500 natural images with carefully annotated boundaries collected from multiple users. The dataset is divided into three parts: 200 for training, 100 for validation and the rest 200 for test.
241 PAPERS • 8 BENCHMARKS
The Semantic Boundaries Dataset (SBD) is a dataset for predicting pixels on the boundary of the object (as opposed to the inside of the object with semantic segmentation). The dataset consists of 11318 images from the trainval set of the PASCAL VOC2011 challenge, divided into 8498 training and 2820 test images. This dataset has object instance boundaries with accurate figure/ground masks that are also labeled with one of 20 Pascal VOC classes.
126 PAPERS • 3 BENCHMARKS
Details It contains 250 outdoor images of 1280$\times$720 pixels each. These images have been carefully annotated by experts on the computer vision field, hence no redundancy has been considered. In spite of that, all results have been cross-checked several times in order to correct possible mistakes or wrong edges by just one subject. This dataset is publicly available as a benchmark for evaluating edge detection algorithms. The generation of this dataset is motivated by the lack of edge detection datasets, actually, there is just one dataset publicly available for the edge detection task published in 2016 (MDBD: Multicue Dataset for Boundary Detection—the subset for edge detection). The level of details of the edge level annotations in the BIPED’s images can be appreciated looking at the GT, see Figs above.
17 PAPERS • 1 BENCHMARK
In order to study the interaction of several early visual cues (luminance, color, stereo, motion) during boundary detection in challenging natural scenes, we have built a multi-cue video dataset composed of short binocular video sequences of natural scenes using a consumer-grade Fujifilm stereo camera (Mély, Kim, McGill, Guo and Serre, 2016). We considered a variety of places (from university campuses to street scenes and parks) and seasons to minimize possible biases. We attempted to capture more challenging scenes for boundary detection by framing a few dominant objects in each shot under a variety of appearances. Representative sample keyframes are shown on the figure below. The dataset contains 100 scenes, each consisting of a left and right view short (10-frame) color sequence. Each sequence was sampled at a rate of 30 frames per second. Each frame has a resolution of 1280 by 720 pixels.
5 PAPERS • 1 BENCHMARK
This dataset is a collection of 1, 2, or 3 images from: BIPED, BSDS500, BSDS300, DIV2K, WIRE-FRAME, CID, CITYSCAPES, ADE20K, MDBD, NYUD, THANGKA, PASCAL-Context, SET14, URBAN10, and the camera-man image. The image selection process consists on computing the Inter-Quartile Range (IQR) intensity value on all the images, images larger than 720×720 pixels were not considered. In dataset whose images are in HR, they were cut. We thank all the datasets owners to make them public. This dataset is just for Edge Detection not contour nor Boundary tasks.
4 PAPERS • 1 BENCHMARK
BRIND is a short name of BSDS-RIND is the first public benchmark that dedicated to studying simultaneously the four edge types, namely Reflectance Edge (RE), Illumination Edge (IE), Normal Edge (NE) and Depth Edge (DE)
3 PAPERS • 1 BENCHMARK
The CID (Campus Image Dataset) is a dataset captured in low-light env with the help of Android programming. Its basic unit is group, which is named by capture time and contains 8 exposure-time-varying raw image shot in a burst.
2 PAPERS • 1 BENCHMARK
The INRIA-Horse dataset consists of 170 horse images and 170 images without horses. All horses in all images are annotated with a bounding-box. The main challenges it offers are clutter, intra-class shape variability, and scale changes. The horses are mostly unoccluded, taken from approximately the side viewpoint, and face the same direction.
2 PAPERS • NO BENCHMARKS YET