Comments (2)
Hi, we also have such blur at edges. This is because the input images are too sparse. In our case, the training is quite stable and converges fast. there is no explicit difference between multiple trainings.
from volrecon.
Hi, we also have such blur at edges. This is because the input images are too sparse. In our case, the training is quite stable and converges fast. there is no explicit difference between multiple trainings.
Thanks for the information.
Then, I will check the training part of my code.
from volrecon.
Related Issues (20)
- How fast is it to do the reconstruction ? HOT 1
- Visualization results HOT 2
- Question about Fine-tuning HOT 3
- Is there a little mistake on confusing SRDF and SDF in Appendix 7 of the paper? HOT 1
- Question about the quantitative evaluation results on DTU dataset HOT 1
- Why is there a difference between the VolRecon and SparseNeus when computing "iter_cos" from "true_cos" in renderer.py? HOT 1
- Issue with tsdf_fusion.sh on custom data
- Approximate training time HOT 1
- loss=nan HOT 2
- Quantitative results HOT 3
- Questions about source views HOT 7
- TypeError: relu(): argument 'input' (position 1) must be Tensor, not float
- depth_fusion HOT 2
- Extract the custom mesh HOT 1
- Volume Rendering of SRDF HOT 5
- Single view reconstruction HOT 1
- camera coordinate in data preprocessing (dtu_train.py) HOT 2
- Error when trying to run pip install -r requirements.txt HOT 1
- how calculate camera parameter ? HOT 1
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 volrecon.