PredictableContextPrior
PredictableContextPrior copied to clipboard
mabaorui
Implementation of CVPR'2022:Surface Reconstruction from Point Clouds by Learning Predictive Context Priors
``` with tf.variable_scope('decoder', reuse=tf.AUTO_REUSE): for i in range(8): with tf.variable_scope("resnetBlockFC_%d" % i ): b_initializer=tf.constant_initializer(0.0) w_initializer = tf.random_normal_initializer(mean=0.0,stddev=np.sqrt(2) / np.sqrt(512)) net = tf.layers.dense(tf.nn.relu(net),512,kernel_initializer=w_initializer,bias_initializer=b_initializer) b_initializer=tf.constant_initializer(-0.5) w_initializer = tf.random_normal_initializer(mean=2*np.sqrt(np.pi) / np.sqrt(512), stddev =...
Hi, thanks for the nice work. Is there any pretrained model available to try? Thank you.
How was the ground truth generated for this? which tools were used?
NeuralPull can learned multiple shapes. use a onehot vector to represent which model to reconstruct. Thank you for your excellent work. Here's a question I want to consult you. 1....
NeuralPull can learned multiple shapes. use a onehot vector to represent which model to reconstruct. Thank you for your excellent work. Here's a question I want to consult you. 1....
Hi, thanks for sharing this code. I wonder when will the Pytorch version released, it seems not easy to follow for this Tensorflow version.
