Comments (3)
Sorry for the confusion. We actually use [100*100*8 tpv resolution, 256 feature dimension] for 3D semantic occupancy prediction and [200*200*16 tpv resolution, 128 feature dimension] for lidar segmentation in the paper. Note that there is no necessary connection between the resolution of the tpv planes and the voxel resolution for visualization, since we can upsample the tpvplanes as shown in Fig. 6 at test time.
On the other hand, finer details could be expected if tpv planes of higher resolution are used.
Also, thanks for reporting the bug to us.
from tpvformer.
I see. Thanks for the reply.
I can understand we can upsample the tpvplanes during test time. But is there any reason not to use 200x200x16 for training in your paper? Did you observe minor improvements when increasing from 100x100x8 (with 2x upsample at test time) to 200x200x16 (no upsample at time time)?
from tpvformer.
In fact, we did not notice substantial improvement qualitatively through visualization, when training with a resolution of 200x200x16. We think it might be due to the sparse nature of LiDAR supervision, which is further sparsified with higher resolution.
from tpvformer.
Related Issues (20)
- Question about 3D OCC task training
- Minimum computer configuration for inference stage? HOT 1
- FileNotFoundError:
- What is config for the released tpv10_lidarseg_v2.pth?
- Why the visualization for lidar segmentation is in voxel?
- nuScenes数据集排列问题 HOT 4
- Higher inference resolution HOT 1
- Scale in metric unit
- Missing keys while loading pre-trained FCOS-3D weights
- got an error result when change the point_cloud_range?
- Question about positional encoding in tpvformer04
- Discrepancy in Parameter Count and FLOPs in Paper
- 为什么推理时还要读lidar bin文件?
- what is mean "Video Context"??
- Pure visual perception? HOT 1
- Visual six perspective angle calculation
- Using different H and W resolution
- How can I use with custom dataset
- error bash launcher.sh config/tpv_lidarseg.py out/tpv_lidarseg
- python visualization/vis_frame.py error
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 tpvformer.