All Projects â†’ zachzeyuwang â†’ tracing-vs-freehand

zachzeyuwang / tracing-vs-freehand

Licence: other
Tracing Versus Freehand for Evaluating Computer-Generated Drawings (SIGGRAPH 2021)

Programming Languages

shell
77523 projects
python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to tracing-vs-freehand

react-sketch-canvas
Freehand vector drawing component for React using SVG as canvas 🖌️
Stars: ✭ 109 (+419.05%)
Mutual labels:  sketching, freehand-drawing
corona-virus
一个冠状病毒肺炎传染病学研究数据集
Stars: ✭ 34 (+61.9%)
Mutual labels:  dataset
pull facebook data for good
[DEPRECATED] Imitate an API for downloading data from Facebook Data For Good
Stars: ✭ 12 (-42.86%)
Mutual labels:  dataset
squad-v1.1-pt
Portuguese translation of the SQuAD dataset
Stars: ✭ 13 (-38.1%)
Mutual labels:  dataset
dataset-histology-landmarks
Dataset: landmarks for registration of histology images
Stars: ✭ 26 (+23.81%)
Mutual labels:  dataset
mxmortalitydb
A data only R package containing all injury intent deaths registered in Mexico from 2004 to 2019
Stars: ✭ 20 (-4.76%)
Mutual labels:  dataset
hubble-otel
Hubble adaptor for OpenTelemetry
Stars: ✭ 29 (+38.1%)
Mutual labels:  tracing
cpytraceafl
CPython bytecode instrumentation and forkserver tools for fuzzing pure python and mixed python/c code using AFL
Stars: ✭ 18 (-14.29%)
Mutual labels:  tracing
user quality
Dataset for Software Evolution and Quality Improvement
Stars: ✭ 27 (+28.57%)
Mutual labels:  dataset
opentelemetry-swift
OpenTelemetry Tracer built for Swift Distributed Tracing
Stars: ✭ 22 (+4.76%)
Mutual labels:  tracing
pump-and-dump-dataset
Additional material for paper: Pump and Dumps in the Bitcoin Era: Real Time Detection of Cryptocurrency Market Manipulations, ICCCN '20
Stars: ✭ 66 (+214.29%)
Mutual labels:  dataset
snorkeling
Extracting biomedical relationships from literature with Snorkel 🏊
Stars: ✭ 56 (+166.67%)
Mutual labels:  dataset
MaskedFaceRepresentation
Masked face recognition focuses on identifying people using their facial features while they are wearing masks. We introduce benchmarks on face verification based on masked face images for the development of COVID-safe protocols in airports.
Stars: ✭ 17 (-19.05%)
Mutual labels:  dataset
Awesome-Deepfakes-Detection
A list of tools, papers and code related to Deepfake Detection.
Stars: ✭ 30 (+42.86%)
Mutual labels:  dataset
covid19-data-greece
Datasets and analysis of Novel Coronavirus (COVID-19) outbreak in Greece
Stars: ✭ 16 (-23.81%)
Mutual labels:  dataset
HAR
Recognize one of six human activities such as standing, sitting, and walking using a Softmax Classifier trained on mobile phone sensor data.
Stars: ✭ 18 (-14.29%)
Mutual labels:  dataset
Audio-Classification-using-CNN-MLP
Multi class audio classification using Deep Learning (MLP, CNN): The objective of this project is to build a multi class classifier to identify sound of a bee, cricket or noise.
Stars: ✭ 36 (+71.43%)
Mutual labels:  dataset
vertx-tracing
Vertx integration with tracing libraries
Stars: ✭ 21 (+0%)
Mutual labels:  tracing
OTT-QA
Code and Data for ICLR2021 Paper "Open Question Answering over Tables and Text"
Stars: ✭ 92 (+338.1%)
Mutual labels:  dataset
BugZoo
Keep your bugs contained. A platform for studying historical software bugs.
Stars: ✭ 49 (+133.33%)
Mutual labels:  dataset

Tracing Versus Freehand for Evaluating Computer-Generated Drawings (SIGGRAPH 2021)

Zeyu Wang, Sherry Qiu, Nicole Feng, Holly Rushmeier, Leonard McMillan, Julie Dorsey

[Paper] [Project] [Browser]

teaser

Drawing Dataset

The dataset consists of 1,498 tracings and freehand drawings by 110 participants for 100 image prompts. Our drawings are registered to the prompts and include vector-based timestamped strokes collected via stylus input.

Please run bash prepare_data.sh to download the dataset, which will be placed in the data folder (about 600MB after unzipping). All code in this repository takes input from the data folder.

data/tracings.json, data/drawings.json, and data/drawings_registered.json use the following format.

{
  // each prompt
  "IMAGE_FILENAME.png": {
    // each drawing
    "PARTICIPANT_ID": [
      // each stroke
      {
        "path": string (Unix timestamp, x, y coordinates at each vertex separated by comma)
        "pressure": string (pressure value at each vertex separated by comma)
        "color": string (hex code, e.g., "#000000")
        "width": integer (stroke width on a 800x800 canvas)
        "opacity": float (alpha value from 0 to 1)
      }
      ...
    ]
    ...
  }
  ...
}

Code

Before running any code, please run conda env create -f environment.yml, conda activate tracer, and sudo apt install librsvg2-bin. All code has been tested on Ubuntu 20.04.

  • utils/ contains the code for rendering drawings and their subsets and composites from the raw JSON data.
  • registration/ contains the code for registering freehand drawings to tracing density.
  • figs/ contains the code for combining intermediate visual results to make the teaser in our paper.

I will update this repo from time to time. If you need anything in particular, please feel free to reach out to me directly.

Citation

The dataset and code are released for academic research use only under CC BY-NC-SA 4.0.

If you use the dataset or code for your research, please cite this paper:

@article{Wang:2021:Tracing,
  author = {Wang, Zeyu and Qiu, Sherry and Feng, Nicole and Rushmeier,  Holly and McMillan, Leonard and Dorsey, Julie},
  title = {Tracing Versus Freehand for Evaluating Computer-Generated Drawings},
  year = {2021},
  issue_date = {August 2021},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  volume = {40},
  number = {4},
  issn = {0730-0301},
  url = {https://doi.org/10.1145/3450626.3459819},
  doi = {10.1145/3450626.3459819},
  journal = {ACM Trans. Graph.},
  month = aug,
  numpages = {12},
  keywords = {sketch dataset, drawing process, stroke analysis}
}
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].