hawp
Wireframe parser
A deep learning framework for parsing wireframes from images, combining supervised and self-supervised learning methods.
Holistically-Attracted Wireframe Parsing [TPAMI'23] & [CVPR' 20]
300 stars
10 watching
52 forks
Language: Python
last commit: 9 months ago cvpr2020deeplsdwireframe
Related projects:
| Repository | Description | Stars |
|---|---|---|
| cherubicxn/neat | A Python project that develops methods to extract wireframe models from neural attraction fields in 3D vision | 54 |
 zhou13/lcnn | A neural network framework for wireframe parsing from images | 505 |
 hszhao/pspnet | A PyTorch implementation of a deep learning model for semantic image segmentation | 1,593 |
 engineering-course/lip_ssl | A deep learning framework for human parsing that learns to detect human structures without explicit joint labeling. | 229 |
 truemedian/hzzp | An HTTP/1.1 parser and encoder written in Zig. | 84 |
 chvancooten/osep-code-snippets | A collection of C# code snippets from an Offensive Security PEN-300 course, covering various topics such as bypassing security features and encoding shellcodes. | 1,160 |
| cherubicxn/afm_cvpr2019 | An implementation of line segment detection using convolutional neural networks and a coupled region coloring problem | 295 |
 eliaskosunen/scnlib | A modern C++ library for safer and more efficient input parsing. | 1,084 |
 taocpp/pegtl | A header-only C++ library for defining and implementing parser combinators using a Parsing Expression Grammar approach | 1,945 |
 m4rw3r/chomp | A fast and expressive monadic-style parser combinator for Rust. | 244 |
 ged/linkparser | An interface to parse and analyze English sentences using the CMU Link Grammar | 76 |
 chrispenner/firefly | A simple Haskell web framework for building lightweight servers with monad-based request handling. | 87 |
 brentp/hts-zig | A wrapper for the Htslib C library to parse VCF files using the Zig programming language | 16 |
 chadwain/rem | A parser for HTML5 documents written in Zig | 106 |
 lxtgh/omg-seg | Develops an end-to-end model for multiple visual perception and reasoning tasks using a single encoder, decoder, and large language model. | 1,300 |