rubenwiersma / deltaconv Goto Github PK
View Code? Open in Web Editor NEWCode for the SIGGRAPH 2022 paper "DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds."
License: MIT License
Code for the SIGGRAPH 2022 paper "DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds."
License: MIT License
Hi @rubenwiersma,
Thx for sharing this excellent work.
While I was going through the paper details, I got confused by the implementation of
Why is the implementation different from that of grad? Can u plz give detailed mathematical expressions for this?
Hi, thanks for your excellent work,
I do some simple tests feeding rotated point clouds into DeltaNetSegmentation
it seems coordinate-independency breaks(output features are different) when using xyz-coordinates as input scalar field,
is it an expected behavior?
should we set constant values to each node to guarantee coordinate-independency?
here is my test code:
# coordinate independent
model = deltaconv.models.DeltaNetSegmentation(1, 256).to('cuda')
# not coordinate independent
# model = deltaconv.models.DeltaNetSegmentation(3, 256).to('cuda')
torch.set_printoptions(precision=2, threshold=10)
pos = torch.randn(100, 3).cuda()
batch_ids = torch.zeros(100).cuda().long()
input = torch.ones(100,1).cuda()
for R in RandomRotations():
pos_r = pos @ R
# coordinate independent
feats = model(DataSeg(pos_r, batch_ids, input))
# not coordinate independent
# feats = model(DataSeg(pos_r, batch_ids))
print(torch.sum(feats, dim=0).detach())
print(feats[5:8].detach())
Hi, first of all thanks for sharing the great work!
I am quite interested in the visualization of the single scalar- or vector feature of each layer (figure 5 in the paper). Can you please also release the codes for the visualization? Thanks a lot!
In transforms/__init__.py
, there is from tkinter import W
. This import seems out of place. Can you please confirm?
This actually caused a issue when using in a docker container with python 3.8.
File "/home/algorithm/.local/lib/python3.8/site-packages/deltaconv/__init__.py", line 4, in <module>
from . import transforms
File "/home/algorithm/.local/lib/python3.8/site-packages/deltaconv/transforms/__init__.py", line 1, in <module>
from tkinter import W
File "/opt/conda/lib/python3.8/tkinter/__init__.py", line 36, in <module>
import _tkinter # If this fails your Python may not be configured for Tk
ImportError: libX11.so.6: cannot open shared object file: No such file or directory
This work is very interesting, I think if I have a group of point clouds with different shapes but all perpendicular to the xy plane (similar to walls with various shapes perpendicular to the ground), can I use your algorithm directly to determine how much they are perpendicular to the ground (some walls are not exactly perpendicular to the ground)
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.