Comments (6)
Hi @StarCycle,
It is not a bug. That coordinates tells the network to which image a particular pixel belongs. For example, it tells whether a pixel belongs to the front image or the top image since the images are arranged in a fixed order along the self.num_img
dimension. Hence, I feel this information could be useful although it could be the case that the network performs fine even without it.
Best,
Ankit
from rvt.
Thank you Ankit!
Oh I get it. It could be useful! But it is still different from the original paper, which says
"Specifically, for each view, we render three image maps with a total of 7 channels: (1) RGB (3 channels), (2) depth (1 channel), and (3) (x, y, z) coordinates of the points in the world frame (3 channels). "
If you use (x, y, z) coordinates, could you please let me know in which line they are calculated? self.pixel_loc[:, 1, :, :] and self.pixel_loc[:, 2, :, :] seems to be (x, y) coordinates in the pixel frame, instead of the world frame
Zhuoheng
from rvt.
The channels for rendering, as mentioned in the paper, are here (RGB + D) and here (x, y, z).
The channels here are in addition to the ones above and are meant to provide position information like in other transformers.
Hope it helps!
from rvt.
Thank you! It's impressive that Pytorch3D can also render coordinates in the world frame! Is it the reason that you chose Pytorch3D, instead of Open3D?
from rvt.
I am not familiar with Open3D but I guess it might be possible to render coordinates with it by feeding in the XYZ instead of RGB. For this project, we chose PyTorch3D because of past experience with it :)
from rvt.
Closing because of inactivity.
from rvt.
Related Issues (20)
- Why is time an essential part of low_dim_state? HOT 2
- Can I run eval.py with multiple processes? HOT 2
- Questions about inference speed HOT 2
- How to train and test with an image_size resolution of 256*256? HOT 4
- About models training HOT 2
- About model training in the real-world HOT 2
- add_final and repeat in replay HOT 4
- [Training] How to evaluate when training? HOT 2
- Questions about the details HOT 5
- About the tp1 in replay HOT 3
- Does the RVT model control Franka robot in Isaac-sim? HOT 4
- Data collection issues HOT 4
- question about camera calibration in real world HOT 8
- AttributeError: 'CustomMultiTaskRLBenchEnv2' object has no attribute 'get_ground_truth_action' HOT 1
- Rendered image with color noise in the background HOT 4
- Question about the up direction of "front" and "back" camera in renderer.py HOT 2
- Details about the real-world experiments HOT 4
- Questions about the scene bounds and img aug in real-robot experiments HOT 4
- Issues while running the training script
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from rvt.