我爱计算机视觉

@AI52CV

微信公众号【我爱计算机视觉】的官方代码仓库

所有 个人的 我参与的
Forks 暂停/关闭的

    我爱计算机视觉/TNN

    推理引擎新选择,腾讯优图开源TNN,ncnn的性能升级版 https://mp.weixin.qq.com/s/G3oOqWSNBKtSSlKRleOAAw 代码原地址:https://github.com/Tencent/TNN

    我爱计算机视觉/dldt

    英特尔重磅开源OpenVINO™ !附送的预训练模型是最大亮点 https://mp.weixin.qq.com/s/Fpj5XVn_cAhErweQwjbQow 代码原地址:https://github.com/opencv/dldt

    我爱计算机视觉/sbd_mask

    思百达公司的sbd_mask 官方称“速度和精度远超百度开源的轻量级口罩检测“ 据内部人士消息,训练集和测试集规模均在万级。 代码原地址:https://github.com/sbdcv/sbd_mask

    我爱计算机视觉/FaceMaskDetection

    AIZOO 的Keras、Caffe、TensorFlow.js 模型 据称算法使用SSD,数据集使用了WIDER Face 和MAFA,训练集6120张图片,验证集1839张图片。 代码原地址:https://github.com/AIZOOTech/FaceMaskDetection

    我爱计算机视觉/Paddle-Lite

    算法代码地址: https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/face_detection Paddle Lite 介绍: https://github.com/PaddlePaddle/Paddle-Lite/

    我爱计算机视觉/reflection-removal

    Robust Reflection Removal with Reflection-free Flash-only Cues 论文:https://arxiv.org/pdf/2103.04273.pdf 代码原地址:https://github.com/ChenyangLEI/flash-reflection-removal

    我爱计算机视觉/shadow-removal

    Auto-Exposure Fusion for Single-Image Shadow Removal 论文:https://github.com/tsingqguo/exposure-fusion-shadow-removal 代码原地址:https://github.com/tsingqguo/exposure-fusion-shadow-removal

    我爱计算机视觉/MPRNet

    Multi-Stage Progressive Image Restoration Paper: https://arxiv.org/abs/2102.02808 代码原地址:https://github.com/swz30/MPRNet

    我爱计算机视觉/MiVOS

    Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion 论文地址:https://github.com/52CV/CVPR-2021-Papers/blob/main 代码原地址:https://github.com/hkchengrex/MiVOS

    我爱计算机视觉/Poly-YOLO

    2020年5月27日发布 论文:https://arxiv.org/abs/2005.13243 相关解读:https://mp.weixin.qq.com/s/mrIqUNqYi6PwlS5bSIr8lg 代码原地址:https://gitlab.com/irafm-ai/poly-yolo

    我爱计算机视觉/BackgroundMattingV2

    Real-Time High Resolution Background Matting 论文地址:https://arxiv.org/abs/2012.07810 解读:https://mp.weixin.qq.com/s/0OJR3Y5cPfeHhdTdI3BgEA 代码原地址:https://github.com/PeterL1n/BackgroundMattingV2

    我爱计算机视觉/RobustNet

    RobustNet: Improving Domain Generalization in Urban-Scene Segmentationvia Instance Selective Whitening 论文地址:https://arxiv.org/abs/2103.15597 代码原地址:https://github.com/shachoi/RobustNet

    我爱计算机视觉/AdvCAM

    Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation 论文地址:https://arxiv.org/abs/2103.08896 代码原地址:https://github.com/jbeomlee93/AdvCAM

    我爱计算机视觉/PLOP

    PLOP: Learning without Forgetting for Continual Semantic Segmentation 论文地址:https://arxiv.org/abs/2011.11390 代码原地址:https://github.com/arthurdouillard/CVPR2021_PLOP

    我爱计算机视觉/Panoptic-PolarNet

    Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation 论文地址:https://arxiv.org/abs/2103.14962 代码原地址:https://github.com/edwardzhou130/Panoptic-PolarNet

    我爱计算机视觉/GrooMeD-NMS

    GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection 论文地址:https://arxiv.org/pdf/2103.17202.pdf 代码原地址:https://github.com/abhi1kumar/groomed_nms

    我爱计算机视觉/3DIoUMatch

    3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection 论文地址:https://arxiv.org/abs/2012.04355 代码原地址:https://github.com/thu17cyz/3DIoUMatch

    我爱计算机视觉/SparseR-CNN

    Sparse R-CNN: End-to-End Object Detection with Learnable Proposals 论文地址:https://arxiv.org/abs/2011.12450 代码原地址:https://github.com/PeizeSun/SparseR-CNN

    我爱计算机视觉/YOLOF

    You Only Look One-level Feature (YOLOF) 论文地址:https://arxiv.org/abs/2103.09460 相关解读:https://mp.weixin.qq.com/s/0ChHOljrqrXk8yWi_S6ITg 代码原地址:https://github.com/megvii-model/YOLOF

    我爱计算机视觉/OWOD

    Towards Open World Object Detection(oral) 论文地址:https://arxiv.org/abs/2103.02603 代码原地址:https://github.com/JosephKJ/OWOD

搜索帮助