Liu Minghua

Would you mind providing a pair of point clouds for me to look into the details?

I think you may try a smaller k. Could you provide the example point clouds for me to take a look?

This PR is about TexturesAtlas, not TexturesUV. When making a texture atlas, the existing solution for handling negative UV coordinates is wrapping faces_verts_uvs at the very beginning, which may lead...

@mengyuest Do you have some new findings?

Thanks for reaching out. In the code, we are using a DFS to enumerate a path (a set of triangle) between u and v, and then try to unfold these...

We will normalize the point cloud before feeding it into the network.

Did you "make" & "make install" libigl? > Hi, > > I'm not familiar with cpp. I've cloned libigl in the data_processing folder and as well as cmake it. However...

According to my experiments, AtlasNet and PCN have much lower Chamfer distance than your TopNet.

In PCN's code, the chamfer distance is calculated as: ``` def chamfer(pcd1, pcd2): dist1, _, dist2, _ = tf_nndistance.nn_distance(pcd1, pcd2) dist1 = tf.reduce_mean(tf.sqrt(dist1)) dist2 = tf.reduce_mean(tf.sqrt(dist2)) return (dist1 + dist2)...

@sheshappanavar I used the TensorFlow version for TopNet. Here are the results_val_300: ``` #ParametersTotal 9965117 #ParametersEncoder 821504 #ParametersDecoder 9143613 plane Generator_emd 0.145209 plane Generator_dist 0.000808 cabinet Generator_emd 0.152978 cabinet Generator_dist...