Open Source Computer Vision Library
ModaNet: A large-scale street fashion dataset with polygon annotations
Some improvements (center sample) about FCOS (FCOS: Fully Convolutional One-Stage Object Detection).
I try my best to keep updated cutting-edge knowledge in Machine Learning/Deep Learning and Natural Language Processing. These are my notes on some good papers
Computer Vision Guide
awesome grounding: A curated list of research papers in visual grounding
Official repository for "CycleISP: Real Image Restoration via Improved Data Synthesis" (CVPR 2020--Oral)
[ICCV 2019] Official implementation of "MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation" in PyTorch + Social Distancing
An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
Image Super Resolution
🔎 Super-scale your images and run experiments with Residual Dense and Adversarial Networks.
TensorFlow implementation of ENet, trained on the Cityscapes dataset.
TensorFlow JS models for MIRNet for low-light image enhancement.
Code and Data Release for GenRe (NeurIPS 2018) and ShapeHD (ECCV 2018)
Deep Learning Autonomous Car based on Raspberry Pi, SunFounder PiCar-V Kit, TensorFlow, and Google's EdgeTPU Co-Processor
A new algorithm for retrieving topological skeleton as a set of polylines from binary images
[ECCV 2020] Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
Stacked Generative Adversarial Networks
UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss
FineGAN: Unsupervised Hierarchical Disentanglement for Fine-grained Object Generation and Discovery
Code for PCN: Point Completion Network in 3DV'18 (Oral)
Fast Scnn Pytorch
A PyTorch Implementation of Fast-SCNN: Fast Semantic Segmentation Network
Cloud-native neural search framework for 𝙖𝙣𝙮 kind of data
Remove watermark automatically(Just can use for fixed position watermark till now). 自动水印消除算法的实现（目前只支持固定水印位置）。
Bmw Yolov4 Inference Api Gpu
This is a repository for an nocode object detection inference API using the Yolov3 and Yolov4 Darknet framework.
A minimal and fast image library for Python and C++
Implementation of Multi-State Constraint Kalman Filter (MSCKF) for Vision-aided Inertial Navigation. This is my master's thesis.
FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)
Automatic colorization using deep neural networks. "Colorful Image Colorization." In ECCV, 2016.
weakly-supervised object detection platform.
[CVPR 2017] Unsupervised deep learning using unlabelled videos on the web
[ECCV'20] Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling
Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition (https://arxiv.org/pdf/2006.11538.pdf)
computer vision framework for tangible interactive surfaces
🍳 Recipes for the Prodigy, our fully scriptable annotation tool
Synthetic Image generation with Flip. Generate thousands of new 2D images from a small batch of objects and backgrounds.
The code repository for "Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions"
[CVPR 2020 Oral] PyTorch implementation of "Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition"
DehazeZoo for collecting dehazing methods, datasets, and codes.
The open-source tool for building high-quality datasets and computer vision models
End-to-End Object Detection Framework - Pluggable to any Training Library: Fastai, Pytorch-Lightning with more to come
The official implementation of Collaborative Video Object Segmentation by Foreground-Background Integration.