All Projects → sinAshish → Rough-Sketch-Simplification-Using-FCNN

sinAshish / Rough-Sketch-Simplification-Using-FCNN

Licence: other
This is a PyTorch implementation of the the Paper by Simo-Sera et.al. on Cleaning Rough Sketches using Fully Convolutional Neural Networks.

Programming Languages

Jupyter Notebook
11667 projects

Projects that are alternatives of or similar to Rough-Sketch-Simplification-Using-FCNN

resilient-swarm-communications-with-meta-graph-convolutional-networks
Meta graph convolutional neural network-assisted resilient swarm communications
Stars: ✭ 49 (+58.06%)
Mutual labels:  research-paper
Sketches
Creative coding sketches made with Java, Processing 3.5.3 and GLSL. Includes a custom GUI.
Stars: ✭ 18 (-41.94%)
Mutual labels:  sketches
notion-scholar
Reference management solution using Python and Notion.
Stars: ✭ 77 (+148.39%)
Mutual labels:  research-paper
Paper Tips And Tricks
Best practice and tips & tricks to write scientific papers in LaTeX, with figures generated in Python or Matlab.
Stars: ✭ 3,099 (+9896.77%)
Mutual labels:  research-paper
react
A wrapper component that allows you to utilise P5 sketches within React apps.
Stars: ✭ 332 (+970.97%)
Mutual labels:  sketches
sketches
HyperLogLog and other probabilistic data structures for mining in data streams
Stars: ✭ 15 (-51.61%)
Mutual labels:  sketches
ML4Sec-papers
Research papers on ML for security
Stars: ✭ 27 (-12.9%)
Mutual labels:  research-paper
virtual sketching
General Virtual Sketching Framework for Vector Line Art (SIGGRAPH 2021)
Stars: ✭ 111 (+258.06%)
Mutual labels:  sketch-simplification
processing-sketchbook
Open Source Sketchbook written in Processing Language
Stars: ✭ 18 (-41.94%)
Mutual labels:  sketches
Fashion-Clothing-Parsing
FCN, U-Net models implementation in TensorFlow for fashion clothing parsing
Stars: ✭ 29 (-6.45%)
Mutual labels:  fully-convolutional-networks
Qlib
Qlib is an AI-oriented quantitative investment platform, which aims to realize the potential, empower the research, and create the value of AI technologies in quantitative investment. With Qlib, you can easily try your ideas to create better Quant investment strategies. An increasing number of SOTA Quant research works/papers are released in Qlib.
Stars: ✭ 7,582 (+24358.06%)
Mutual labels:  research-paper
EnviroDIY Mayfly Logger
hardware design files, example code sketches, and documentation for Arduino-framework EnviroDIY Mayfly data logger
Stars: ✭ 25 (-19.35%)
Mutual labels:  sketches
STAWM
Code for the paper 'A Biologically Inspired Visual Working Memory for Deep Networks'
Stars: ✭ 21 (-32.26%)
Mutual labels:  sketches
annotated research papers
This repo contains annotated research papers that I found really good and useful
Stars: ✭ 2,101 (+6677.42%)
Mutual labels:  research-paper
fuzzymax
Code for the paper: Don't Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word Vectors, ICLR 2019.
Stars: ✭ 43 (+38.71%)
Mutual labels:  research-paper
letter-2-reviewers-LaTeX-template
A LaTeX template to write response letters for journal revisions
Stars: ✭ 32 (+3.23%)
Mutual labels:  research-paper
PaperShell
Nice and flexible template environment for papers written in LaTeX
Stars: ✭ 117 (+277.42%)
Mutual labels:  research-paper
3d-prostate-segmentation
Segmentation of prostate from MRI scans
Stars: ✭ 36 (+16.13%)
Mutual labels:  fully-convolutional-networks
Sketch2Color-anime-translation
Given a simple anime line-art sketch the model outputs a decent colored anime image using Conditional-Generative Adversarial Networks (C-GANs) concept.
Stars: ✭ 90 (+190.32%)
Mutual labels:  implementation-of-research-paper
bullet-core
Bullet is a streaming query engine that can be plugged into any singular data stream using a Stream Processing framework like Apache Storm, Spark or Flink.
Stars: ✭ 36 (+16.13%)
Mutual labels:  sketches

Rough Sketch-Simplification using Deep Learning

This is a PyTorch implementation of the the Paper by Simo-Sera et.al. on Cleaning Rough Sketches using Fully Convolutional Neural Networks.

I even wrote a blog article on medium explaining the complete paper.

Original Paper

Dependencis

  • PyTorch
  • PIL
  • hd5y
  • numpy
  • pandas

Noteable Issues with the Implementation

The major problem is with the availability of the proper dataset used by the authors. Hence, the reproducibilty issues.
And availability of a GPU too. I don't have one.

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].