5,337
edits
Line 52: | Line 52: | ||
The encoder converts images into latent points. | The encoder converts images into latent points. | ||
It consists of | It consists of 8 convolutional blocks which each downsample the feature map. (Note that the paper says 7 but their code uses 8) | ||
Each block is: Conv-BatchNorm-LeakyReLU. | Each block is: Conv-BatchNorm-LeakyReLU. | ||
The output of the convolutional blocks are put through a fully connected layer and reshaped into a \(200 \times 3\) matrix. | The output of the convolutional blocks are put through a fully connected layer and reshaped into a \(200 \times 3\) matrix. | ||
The decoder renders the latent points into a depth map from the target view. | The decoder renders the latent points into a depth map from the target view. | ||
It consists of | It consists of 8 blocks of: Upsample-Conv-BatchNorm-LeakyReLU. | ||
They use bilinear upsampling. | They use bilinear upsampling. | ||
* Optimizer: Adam | |||
** learning_rate=0.00006, beta_1=0.5, beta_2=0.999 | |||
==Evaluation== | ==Evaluation== |