All Projects → ZHKKKe → PPM

ZHKKKe / PPM

Licence: other
A High-Quality Photograpy Portrait Matting Benchmark

Projects that are alternatives of or similar to PPM

benchmark-malloc
Trace memory allocations and collect stats
Stars: ✭ 18 (-51.35%)
Mutual labels:  benchmark
iohk-monitoring-framework
This framework provides logging, benchmarking and monitoring.
Stars: ✭ 27 (-27.03%)
Mutual labels:  benchmark
criterion-compare-action
⚡️📊 Compare the performance of Rust project branches
Stars: ✭ 16 (-56.76%)
Mutual labels:  benchmark
mini-nbody
A simple gravitational N-body simulation in less than 100 lines of C code, with CUDA optimizations.
Stars: ✭ 73 (+97.3%)
Mutual labels:  benchmark
BIRL
BIRL: Benchmark on Image Registration methods with Landmark validations
Stars: ✭ 66 (+78.38%)
Mutual labels:  benchmark
liar
Flexible, stand-alone benchmarking
Stars: ✭ 16 (-56.76%)
Mutual labels:  benchmark
fizzboom
Benchmark to compare async web server + interpreter + web client implementations across various languages
Stars: ✭ 46 (+24.32%)
Mutual labels:  benchmark
Knowledge distillation via TF2.0
The codes for recent knowledge distillation algorithms and benchmark results via TF2.0 low-level API
Stars: ✭ 87 (+135.14%)
Mutual labels:  benchmark
autobench
Benchmark your application on CI
Stars: ✭ 16 (-56.76%)
Mutual labels:  benchmark
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 (-54.05%)
Mutual labels:  benchmark
hyperspectral-soilmoisture-dataset
Hyperspectral and soil-moisture data from a field campaign based on a soil sample. Karlsruhe (Germany), 2017.
Stars: ✭ 23 (-37.84%)
Mutual labels:  benchmark
MVP Benchmark
MVP Benchmark for Multi-View Partial Point Cloud Completion and Registration
Stars: ✭ 74 (+100%)
Mutual labels:  benchmark
IGUANA
IGUANA is a benchmark execution framework for querying HTTP endpoints and CLI Applications such as Triple Stores. Contact: [email protected]
Stars: ✭ 22 (-40.54%)
Mutual labels:  benchmark
react-native-css-in-js-benchmarks
CSS in JS Benchmarks for React Native
Stars: ✭ 46 (+24.32%)
Mutual labels:  benchmark
FewCLUE
FewCLUE 小样本学习测评基准,中文版
Stars: ✭ 251 (+578.38%)
Mutual labels:  benchmark
benchbox
🧀 The Benchmark Testing Box
Stars: ✭ 19 (-48.65%)
Mutual labels:  benchmark
json-serialization-benchmarking
Miscellaneous benchmarks for JSON serialization on JVM/Android
Stars: ✭ 48 (+29.73%)
Mutual labels:  benchmark
Long-Map-Benchmarks
Benchmarking the best way to store long, Object value pairs in a map.
Stars: ✭ 32 (-13.51%)
Mutual labels:  benchmark
tls-perf
TLS handshakes benchnarking tool
Stars: ✭ 18 (-51.35%)
Mutual labels:  benchmark
glassbench
A micro-benchmark framework to use with cargo bench
Stars: ✭ 29 (-21.62%)
Mutual labels:  benchmark
- A Photography Portrait Matting Benchmark -

News | Introduction | Download | License | Citation | Contact


News

  • [Jul 20 2021] PPM-100 Benchmark is Released!
    The benchmark with 100 finly-annotated, high-resolution images (PPM-100) is released.

Introduction

PPM is a portrait matting benchmark with the following characteristics:

  • Fine Annotation - All images are labeled and checked carefully.
  • Natural Background - All images use the original background without replacement.
  • Rich Diversity - The images cover full/half body and various postures.
  • High Resolution - The resolution of images is between 1080p and 4k.

Following is an example image:

Download

Currently, PPM-100 used in the MODNet paper is available.
Note that few images used in the MODNet paper are replaced by similar images due to license issues.
You can download PPM-100 from:
Google Drive | 百度网盘 (提取码: PPMB)

License

All original portrait images in PPM are from Flickr and constrained by Flickr Creative Commons License (Commercial use & mods allowed).
All annotated alpha mattes in PPM are released under the Creative Commons Attribution NonCommercial ShareAlike 4.0 license.

Citation

If you use this PPM benckmark, please cite:

@article{MODNet,
  author = {Zhanghan Ke and Kaican Li and Yurou Zhou and Qiuhua Wu and Xiangyu Mao and Qiong Yan and Rynson W.H. Lau},
  title = {Is a Green Screen Really Necessary for Real-Time Portrait Matting?},
  journal={ArXiv},
  volume={abs/2011.11961},
  year = {2020},
}

Contact

This repository is currently maintained by Zhanghan Ke (@ZHKKKe).
If there is any question, please contact [email protected].

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].