hkust-vgd / riconv Goto Github PK
View Code? Open in Web Editor NEWRotation Invariant Convolutions for 3D Point Clouds Deep Learning
Home Page: https://hkust-vgd.github.io/riconv/
License: MIT License
Rotation Invariant Convolutions for 3D Point Clouds Deep Learning
Home Page: https://hkust-vgd.github.io/riconv/
License: MIT License
Hi, authors,
According to Section 5 (5.1) in your paper, three test cases of z/z, SO3/SO3, z/SO3 rotation are performed for comparison. However, I couldn't find the corresponding parts in your package riconv. Could you release the related parts in code?
Thanks!
Thank you so much for sharing the codes. Could you please share the code for visualizing the test results for part segmentation?
hi, my friends. Thank you for your work!
I want to know if have write the evaluate code? if yes,please share it.
Hi,
I am currently working on a literature preview project.
Is it possible to provide the pre-trained models you used for us to test?
Thank you in advance?
Could you please provide a docker? I've tried my best to configure the environment, but there's still something with it
Thanks for your excellent work and code! I have a question here.
The origin paper said that The local space is then uniformly divided into several bins along pm # » however, the meaning of the code is that local space is uniformly divided into several bins along m(blue dot) to the centre of all dots rather than m(blue dot) to p(red dot), is it an error or you changed the strategy?
mean_local = tf.reduce_mean(nn_pts, axis=-2, keepdims=True)
mean_global = tf.reduce_mean(pts, axis=-2, keepdims=True)
mean_global = tf.expand_dims(mean_global, axis=-2)
nn_pts_local_mean = tf.subtract(nn_pts, mean_local, name=tag + 'nn_pts_local_mean')
dists_local_mean = tf.norm(nn_pts_local_mean, axis=-1, keepdims=True) # dist to local mean
vec = mean_local - nn_pts_center
vec_dist = tf.norm(vec, axis=-1, keepdims =True)
vec_norm = tf.divide(vec, vec_dist)
vec_norm = tf.where(tf.is_nan(vec_norm), tf.ones_like(vec_norm) * 0, vec_norm)
nn_pts_local_proj = tf.matmul(nn_pts_local, vec_norm, transpose_b=True)
nn_pts_local_proj_dot = tf.divide(nn_pts_local_proj, dists_local)
nn_pts_local_proj_dot = tf.where(tf.is_nan(nn_pts_local_proj_dot), tf.ones_like(nn_pts_local_proj_dot) * 0, nn_pts_local_proj_dot) # check nan
nn_pts_local_proj_2 = tf.matmul(nn_pts_local_mean, vec_norm, transpose_b=True)
nn_pts_local_proj_dot_2 = tf.divide(nn_pts_local_proj_2, dists_local_mean)
nn_pts_local_proj_dot_2 = tf.where(tf.is_nan(nn_pts_local_proj_dot_2), tf.ones_like(nn_pts_local_proj_dot_2) * 0, nn_pts_local_proj_dot_2) # check nan
nn_fts = tf.concat([dists_local, dists_local_mean, nn_pts_local_proj_dot, nn_pts_local_proj_dot_2], axis=-1) # d0 d1 a0 a1
# compute indices from nn_pts_local_proj
_**vec = mean_global - nn_pts_center**_
vec_dist = tf.norm(vec, axis=-1, keepdims =True)
vec_norm = tf.divide(vec, vec_dist)
**nn_pts_local_proj = tf.matmul(nn_pts_local, vec_norm, transpose_b=True)**
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.