Comments (3)
Another question is about the description in Section4.4 Key-scans selection and refinement
Additionally, to improve the efficiency of the refinement process, only rays or LiDAR points within a truncation distance dt based on the point density are included.
It seems that the final key-scans based optimization only consider the region where the lidar points are dense, and this truncation distance dt has nothing to do with the parameter truncation Tr mentioned before in the paper.
I understand right?
from nerf-loam.
Hi, marrblue.
For sampling, we need sample points inside the voxel. As the voxel size changes, we cannot define a specific sampling step, e.g., sampling points with a 0.1 m gap. So the "step size ratio" is used to define the step size: step_size = step_size_ratio * voxel_size. You can consider "step size" as the sampling gap. If you want to know more about the "step size“, you can refer to Algorithm 1 of the paper Neural Sparse Voxel Fields. This is also the sampling strategy we adopt.
For truncation distance
from nerf-loam.
Hi @JunyuanDeng Thank you for your informative reply and good luck with the early acceptance of the paper : )
I will close this issue.
from nerf-loam.
Related Issues (20)
- cuda out of memory HOT 2
- 可视化 HOT 1
- patchwork_module_path ="/xxx/patchwork-plusplus/build/python_wrapper" HOT 6
- python demo/run.py configs/kitti/kitti_00.yaml HOT 3
- torch.cuda.OutOfMemoryError HOT 17
- AttributeError: module 'grid' has no attribute 'svo_intersect' HOT 13
- The Process Freezes When Dealing with a Large Number of Frames HOT 3
- IndexError: select(): index 108605 out of range for tensor of size [69829, 4] at dimension 0 HOT 4
- RuntimeError: CUDA out of memory. HOT 3
- whether Need groundtruth pose ? HOT 1
- AttributeError: 'NoneType' object has no attribute 'cuda' HOT 5
- AttributeError: module 'grid' has no attribute 'svo_intersect' HOT 1
- 关于编译patchwork-plusplus的问题
- NaN Result in OptimizablePose Class with Orthogonal Matrix of Determinant -1 HOT 1
- 关于patchwork++的问题 HOT 2
- Continuity HOT 2
- svo init HOT 2
- eval issue HOT 2
- 八叉树代码的困惑 HOT 2
- code confusion
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 nerf-loam.