Comments (5)
For example, we split the San Francisco dataset as training dataset and test dataset, and train the training dataset as one block, can we get better result on test dataset?
from unboundednerfpytorch.
This is a good question. In fact, the generalization of NeRF is a hard topic from my point of view. In the real world, two different places may have different physical properties (reflexity, density, etc). However, the physical laws (including the rendering law, Newton's laws, etc) keep constant when going from one place to another. We cannot guarantee that we can generalize the NeRF from one place to another. However, when testing NeRF performances, we can still sample from the local block so that we can generalize from training views to unseen views.
from unboundednerfpytorch.
Closed because of no further comment.
from unboundednerfpytorch.
Yes, exactly. Except reflection, density, a lots of factors have influence on the generalization of NeRF. Movable object(vehicles, pedestrians, etc.) is also one of factors? because the collected sensors take photos at one place with different time in my dataset, which causes same place with different feature(color). sometime with movable object, sometimes not. If we remove the object like waymo, that is a expensive engineer.
Btw, 2D rendering head maybe easier than depth output head? Because sometime we want to get reconstruct 3D scene from depth info. It's hard to keep consistent on same object and get better result on whole image.
from unboundednerfpytorch.
Yes, you are absolutely correct.
from unboundednerfpytorch.
Related Issues (20)
- 运行系统问题
- 运行系统问题 HOT 3
- RuntimeError: Error building extension 'segment_cumsum_cuda' #7 HOT 3
- No module named 'adam_upd_cuda' HOT 5
- 请教 HOT 3
- RuntimeError: Error building extension 'segment_cumsum_cuda' HOT 2
- 训练进程自动退出 HOT 6
- 测试nuscene数据集 HOT 3
- 请教一下运行自己数据的问题 HOT 3
- 训练图片下采样问题 HOT 1
- 渲染视频相机视角问题 HOT 2
- 请问这个训练配置,是对应190G的原始waymo数据, 还是19G的processed 的数据集?
- Export to point clouds HOT 1
- RuntimeError: configuration file type HOT 2
- Could contributor update the latest NeRF information plz HOT 1
- A question about the transformation matrix for San Fran Cisco Mission Bay dataset HOT 1
- How to obtain the appearance embedding? HOT 1
- Question about moving object HOT 2
- A question about the c2w matrix for San Fran Cisco Mission Bay dataset 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 unboundednerfpytorch.