Comments (5)
Hi, we did not define the near and far like the bounded scene in NeRF, but we define the real size of the voxel. Here, we calculate the sampled point within the X ∈ (−52m, 52m), Z ∈ (0m, 6m), and Y ∈ (−52m, 52m).
self.Z = 16
self.Y = 256
self.X = 256
self.stepsize =0.5
N_samples = int(np.linalg.norm(np.array([self.Z // 2, self.Y // 2, self.X // 2]) + 1) / self.stepsize) + 1
The density of the sampled point out of the voxel would be set as 0, and the last sampled point is explicitly set as 1.
from simpleoccupancy.
In our experiment, we define the Z above the ego coordinate. You may also set the range in [-5, 3]. The voxel is defined in the ego coordinate, not the lidar coordinate.
from simpleoccupancy.
Isn't voxel predicted in the lidar coordinate system? Why is the real size range of Z not [-5, 3] but [0, 6]
Hi, we did not define the near and far like the bounded scene in NeRF, but we define the real size of the voxel. Here, we calculate the sampled point within the X ∈ (−52m, 52m), Z ∈ (0m, 6m), and Y ∈ (−52m, 52m).
self.Z = 16 self.Y = 256 self.X = 256 self.stepsize =0.5
N_samples = int(np.linalg.norm(np.array([self.Z // 2, self.Y // 2, self.X // 2]) + 1) / self.stepsize) + 1
The density of the sampled point out of the voxel would be set as 0, and the last sampled point is explicitly set as 1.
Isn't voxel predicted in the lidar coordinate system? Why is the real size range of Z not [-5, 3] but [0, 6]
from simpleoccupancy.
One more question,Is the rendering 95ms in the paper run on the existing cuda acceleration implementation or torch?
from simpleoccupancy.
just with the torch implementation
from simpleoccupancy.
Related Issues (18)
- About the depth loss and volume rendering sampling strategy HOT 2
- How long did it take you to train the model? HOT 1
- How can I get the point_cloud_label? The file export_point_cloud_nuscenes seems to work incorrectly,btw..... HOT 2
- Why do you mask the feat here? HOT 2
- Why is this gt label not from the point cloud? HOT 1
- Why do you flip the xyz here?
- pretrained weights HOT 2
- why cumsum the prob to render the depth HOT 5
- Questions about depth map visualization and depth rendering HOT 4
- Questions about F.grid_sample()
- Supplements? HOT 2
- Release of source code and pretrained weights HOT 4
- Rendering depth too slow HOT 2
- requirements.txt HOT 2
- Poind Cloud Processing for nuScenes? HOT 2
- Visualization implementation HOT 2
- Question about GPU memory requiments for training and evaluation respectively? HOT 4
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 simpleoccupancy.