Comments (2)
Thank you for using our model.
I believe that the effect comes from the saving part, the output depth of our model is metrics depth, thus is has floating values from [0.0, +inf), which can result in PIL saving the image in the wrong format.
I suggest you first convert the scalar float values to RGB with a colormap transformation and then save it. You can look into idisc/utils/visualization.py, more specifically into colorize function. It accepts 2D inputs (e.g., (H, W) shaped numpy array), min and max values (for NYU is 0.01 and 10.0 meters), and the colormap name. For instance, "magma" is a good colormap choice since it has a perceptually increasing colormap and does not introduce wrong spurious contrasts.
One little nitpick: the model was trained with ImageNet normalization statistics, hence it would be better to normalize the RGB image with those, instead of the default ones, i.e., {"mean": [0.5, 0.5, 0.5], "std": [0.5, 0.5, 0.5]}
from idisc.
Hi @lpiccinelli-eth, this solves it!
Thank you so much for your response and detailed explanation!
from idisc.
Related Issues (20)
- I want to visualize your results, but you don't seem to use visulization.py in your code, where should I use them HOT 3
- Can you tell me about the steps you do to normalize the input depth image? HOT 1
- I want to verify your nyunormal results, but the results I ran out were different from yours, and I wanted to know what went wrong and how to run your results
- The evaluation index of the prediction result of the table plane normal vector estimation is printed incorrectly HOT 1
- How to test the depth of a picture
- Cannot import 'MultiScaleDeformableAttention' HOT 4
- AttributeError: 'IDisc' object has no attribute 'no_sync' HOT 2
- Question about Diode indoor dataset HOT 2
- Surface Normal Estimation procedure
- Question about outdoor zeroshot datasets HOT 2
- Evaluating on KITTI Improved Ground Truth HOT 1
- Abnormal Training Phenomena and Bad Performance HOT 6
- _IncompatibleKeys failure loading weights. HOT 1
- About the results of my own test picture are inconsistent with the paper HOT 5
- question about geometrical data augmentation HOT 3
- NYU dataset normal annotation missing HOT 1
- Internal Discretization Figure HOT 6
- "ModuleNotFoundError: No module named 'idisc'" when running test.py HOT 3
- Question : How is GT-Based Depth Rescaling for Diode Indoor Dataset performed ? HOT 2
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 idisc.