CVPR2020最新15篇论文开源代码!!!

关注上方深度学习技术前沿,选择“星标公众号”

资源干货,第一时间送达!


全球计算机视觉顶级会议CVPR2020 (IEEE Conference on Computer Vision and Pattern Recognition,即IEEE国际计算机视觉与模式识别会议) 即将于2020年6月14日-19日在美国西雅图召开。本届大会总共录取来自全球论文1470篇,接收率为22%,相比去年降低3个百分点,竞争越来越激烈。本届大会涵盖人体识别、基于图像建模、计算摄影与图像、视频分析与事件识别、脸部和手势分析、文件分析、统计方法与学习等多个主题。

本文整理了15篇接收论文的代码实现,以便大家阅览学习。这些论文包括姿态估计、深度估计、目标跟踪、实例分割、对抗生成网络、3D点云、面部表情识别、神经网络等。

1. GhostNet: More Features from Cheap Operations(超越Mobilenet v3的架构)

We beat other SOTA lightweight CNNs such as MobileNetV3 and FBNet.

论文:https://arxiv.org/pdf/1911.11907

代码:https://github.com/iamhankai/ghostnet

2. 姿态估计,Distribution Aware Coordinate Representation for Human Pose Estimation

论文:https://arxiv.org/abs/1910.06278

代码:https://github.com/ilovepose/DarkPose

作者团队主页:https://ilovepose.github.io/coco/

3. 实例跟踪,CenterMask : Real-Time Anchor-Free Instance Segmentation

论文:https://arxiv.org/abs/1911.06667

代码:https://github.com/youngwanLEE/CenterMask

4. 实例跟踪,Deep Snake for Real-Time Instance Segmentation

论文:https://arxiv.org/abs/2001.01629

代码:https://github.com/zju3dv/snake

5. 2D人体姿态估计,The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation

论文:https://arxiv.org/abs/1911.07524

代码:https://github.com/HuangJunJie2017/UDP-Pose

解读:https://zhuanlan.zhihu.com/p/92525039

6. 2D人体姿态估计Distribution-Aware Coordinate Representation for Human Pose Estimation

论文:https://arxiv.org/abs/1910.06278

代码:https://github.com/ilovepose/DarkPose

73D人体姿态估计,VIBE: Video Inference for Human Body Pose and Shape Estimation

论文:https://arxiv.org/abs/1912.05656

代码:https://github.com/mkocabas/VIBE

8. 单目深度估计,Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation

论文:https://arxiv.org/abs/2002.12114

代码:https://github.com/yzhao520/ARC

9. 图像调和, Deep Image Harmonization via Domain Verification

论文:https://arxiv.org/abs/1911.13239

代码:https://github.com/bcmi/Image_Harmonization_Datasets

10. 点云分类,PointAugment: an Auto-Augmentation Framework for Point Cloud Classification

论文:https://arxiv.org/abs/2002.10876

代码:https://github.com/liruihui/PointAugment/

11.场景文本识别,ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network

论文:https://arxiv.org/abs/2002.10200

代码:https://github.com/Yuliang-Liu/bezier_curve_text_spotting

12.3dCNN压缩,Frequency Domain Compact 3D Convolutional Neural Networks

论文:https://arxiv.org/pdf/1909.04977arxiv.org

代码:https://github.com/huawei-noah/CARSgithub.com

13.CARS: Contunuous Evolution for Efficient Neural Architecture Search(连续进化的NAS)

论文:https://arxiv.org/pdf/1909.04977.pdf

代码:https://github.com/huawei-noah/CARS

14.实例分割PolarMask: Single Shot Instance Segmentation with Polar Representation

论文链接:https://arxiv.org/abs/1909.13226

论文解读:https://zhuanlan.zhihu.com/p/84890413

开源代码:https://github.com/xieenze/PolarMask

15.面部表情识别Suppressing Uncertainties for Large-Scale Facial Expression Recognition

论文链接:https://arxiv.org/abs/2002.10392

开源代码:https://github.com/kaiwang960112/Self-Cure-Network

???? 更多精彩咨讯,长按识别,即可关注

  • 0
    点赞
  • 8
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值