TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/Scribble

Scribble

ImagesUnknownIntroduced 2019-09-24

Scribble is a new outline dataset consisting of 200 images (150 train, 50 test) for each of 10 classes – basketball, chicken, cookie, cupcake, moon, orange, soccer, strawberry, watermelon and pineapple. All the images have a white background and were collected using search keywords on popular search engines. In each image, we obtain rough outlines for the image. We find the largest blob in the image after thresholding it into a black and white image. We fill the interior holes of the largest blob and obtain a smooth outline using the SavitzkyGolay filter.

Source: https://arxiv.org/pdf/1909.11081v2.pdf

Benchmarks

Sketch-to-Image Translation/FIDSketch-to-Image Translation/AccuracySketch-to-Image Translation/Human (%)

Related Benchmarks

ScribbleKITTI/10-shot image generation/mIoUScribbleKITTI/10-shot image generation/mIoU (1% Labels)ScribbleKITTI/10-shot image generation/mIoU (10% Labels)ScribbleKITTI/10-shot image generation/mIoU (20% Labels)ScribbleKITTI/10-shot image generation/mIoU (50% Labels)ScribbleKITTI/10-shot image generation/mIoU-1%ScribbleKITTI/3D Semantic Segmentation/mIoUScribbleKITTI/3D Semantic Segmentation/mIoU-1%ScribbleKITTI/Semantic Segmentation/mIoUScribbleKITTI/Semantic Segmentation/mIoU (1% Labels)ScribbleKITTI/Semantic Segmentation/mIoU (10% Labels)ScribbleKITTI/Semantic Segmentation/mIoU (20% Labels)ScribbleKITTI/Semantic Segmentation/mIoU (50% Labels)ScribbleKITTI/Semantic Segmentation/mIoU-1%

Statistics

Papers
8
Benchmarks
3

Links

Homepage

Tasks

Sketch-to-Image Translation