JianqiangWan / Super Bpd
Licence: apache-2.0
Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation (CVPR 2020)
Stars: ✭ 153
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Super Bpd
rt-mrcnn
Real time instance segmentation with Mask R-CNN, live from webcam feed.
Stars: ✭ 47 (-69.28%)
Mutual labels: real-time, image-segmentation
Signals
General purpose modern C++ Signal-Slot providing ease of use, flexibility and extremely high performance aiming to replace traditional interfaces in real-time applications
Stars: ✭ 137 (-10.46%)
Mutual labels: real-time
Tensorflowtts
😝 TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
Stars: ✭ 2,382 (+1456.86%)
Mutual labels: real-time
Vidgear
A High-performance cross-platform Video Processing Python framework powerpacked with unique trailblazing features 🔥
Stars: ✭ 2,048 (+1238.56%)
Mutual labels: real-time
Real Time Ml Project
A curated list of applied machine learning and data science notebooks and libraries across different industries.
Stars: ✭ 143 (-6.54%)
Mutual labels: real-time
Hedgedoc
HedgeDoc - The best platform to write and share markdown.
Stars: ✭ 2,498 (+1532.68%)
Mutual labels: real-time
Coinpusher
📈 real-time cryptocurrency chart prediction based on neuronal-networks
Stars: ✭ 141 (-7.84%)
Mutual labels: real-time
Azure Event Hubs Spark
Enabling Continuous Data Processing with Apache Spark and Azure Event Hubs
Stars: ✭ 140 (-8.5%)
Mutual labels: real-time
Gccpm Look Into Person Cvpr19.pytorch
Fast and accurate single-person pose estimation, ranked 10th at CVPR'19 LIP challenge. Contains implementation of "Global Context for Convolutional Pose Machines" paper.
Stars: ✭ 137 (-10.46%)
Mutual labels: real-time
Optical Flow Filter
A real time optical flow algorithm implemented on GPU
Stars: ✭ 146 (-4.58%)
Mutual labels: real-time
Filament
Filament is a real-time physically based rendering engine for Android, iOS, Windows, Linux, macOS, and WebGL2
Stars: ✭ 13,215 (+8537.25%)
Mutual labels: real-time
Multi Task Refinenet
Multi-Task (Joint Segmentation / Depth / Surface Normas) Real-Time Light-Weight RefineNet
Stars: ✭ 139 (-9.15%)
Mutual labels: real-time
Tf unet
Generic U-Net Tensorflow implementation for image segmentation
Stars: ✭ 1,802 (+1077.78%)
Mutual labels: image-segmentation
Msg Net
Multi-style Generative Network for Real-time Transfer
Stars: ✭ 152 (-0.65%)
Mutual labels: real-time
Super-BPD for Fast Image Segmentation (CVPR 2020)
Introduction
We propose direction-based super-BPD, an alternative to superpixel, for fast generic image segmentation, achieving state-of-the-art real-time result.
Citation
Please cite the related works in your publications if it helps your research:
@InProceedings{Wan_2020_CVPR,
author = {Wan, Jianqiang and Liu, Yang and Wei, Donglai and Bai, Xiang and Xu, Yongchao},
title = {Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation},
booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}
Prerequisite
- pytorch >= 1.3.0
- g++ 7
Dataset
- Download the BSDS500 & PascalContext Dataset, and unzip it into the
Super-BPD/folder.
Testing
- Compile cuda code for post-process.
cd post_process
python setup.py install
-
Download the pre-trained PascalContext model and put it in the
savedfolder. -
Test the model and results will be saved in the
test_pred_flux/PascalContextfolder. -
SEISM is used for evaluation of image segmentation.
Training
- Download VGG-16 pretrained model.
python train.py --dataset PascalContext
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].