Comments (3)
Hi Todd-Qi,
Thank you for your interest in our project.
Regarding your questions:
The final training loss of our pre-trained model is also around 50, so your final loss is reasonable.
However we used batch size 16 on training. Smaller batch size may cause more noise during training.
And about your result, what numbers have you got on DTU dataset?
Could you please provide the evaluation parameters and fusion parameters you used to get the result?
Cheers,
Jiayu
from cvp-mvsnet.
Hello, @JiayuYANG
I'm using the same fusion parameter, i.e. prob_threshold=0.8
, disp_threshold=0.13
and num_consistent=3
.
I think the problem comes from the predicted depth map. The depth map of mine has many holes.
from the top to bottom, (a)the original ref image, (b)the depth map predicted by my trained model, (c)the depth map predicted by your pretrained model.
For the evaluation, the number of depth sampling is 48.
In addition, I compute the mean absolute error(MAE) on the DTU validtion set. The MAE of your pretrained model is about 10 while my trained model is about 15.
Do you have any suggestions how to solve this problem?
Thank You!
from cvp-mvsnet.
Hi Todd-Qi,
I have updated our code to solve this issue,
you may pull the latest version to reproduce our results.
Training from scratch using default settings, the latest version can produce following results on my machine.
acc. | comp. | overall |
---|---|---|
0.3032 | 0.4161 | 0.3597 |
Cheers,
Jiayu
from cvp-mvsnet.
Related Issues (20)
- Can you provide your 3D point clouds for DTU test set?
- Normal Map HOT 2
- returned value in calDepthHypo HOT 3
- How to load checkpoint(.ckpt) in test code? HOT 1
- ERROR HOT 3
- generalization ability(泛化能力) of neural network based MVS HOT 2
- Tank test
- RuntimeError: cuda runtime error (710) : device-side assert triggered at
- 自采数据 HOT 1
- Pixel Interval
- Running inference on 8GB RTX 3070
- 自采数据集的参数设置
- License
- What is "disp.dmb" in "outputs_pretrained/fusibile_fused"?How to understand this?
- datasets request
- 如何使用自己录制的数据集
- Found 0.00 million points HOT 1
- Matlab Evaluation
- Thank you for your work. Where can I download the supplementary materials mentioned in your paper?
- Environmental conflicts
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 cvp-mvsnet.