HyperSphereSurfaceRegression 算法笔记
360 Surface Regression with a Hyper-Sphere Loss归纳表格总结CNN architectureArchitectureA fully convolutional (FCN) encoder-decoder network with skip-connections, based on UNet combined with a VGG16 encoder.EncoderThe same as conv1-conv5 in VGG1
原创
2021-05-04 18:42:19 ·
293 阅读 ·
0 评论