Comments (3)
Hi, @alekovargas
Thanks for your interest in our work. I haven't tried to train PoinTr on Single category before, but it is nice to see the results from you.
From your results and descriptions, PoinTr can work well on the coarse(center) prediction in your setting. However, the detail local geometry can not be correctly inferred. I think there maybe two reasons:
- In the training pipeline, local geometry is weakly supervised by an CD between the complete shapes, not the local regions. And CD loss, to some extend, is suboptimal in shape reconstruction problems.
- The problem is too challenge. I am curious about the drop ratio when you evaluate the model ( and visualize the results). The model trained on fewer samples may lack of generalization ability to all incomplete patterns. And for those situations where the missing parts contain complex geometry patterns (beyond simple flat surfaces), the model may need more samples or more parameters. (the head and wings of airplane can be completed well by PoinTr, but for earphone, bottle, PoinTr performes worse)
For the first point, can we add a local shape reconstruction loss to constrain more on the local geometry? And for loss between overall shapes, I haven't try to optimize EMD loss during the training of PoinTr, which worths a try.
For the second point, if your situation does not allow you to have many samples, i think more augmentations maybe helpful. In may codebase, i only use random-crop for the samples in ShapeNet-55.
Hope it can help you.
Best!
from pointr.
Close it since no response. Feel free to re-open it if problems still exist
from pointr.
sorry for the late replay,
Yes more augmentation data solved the problem, thanks for such nice work.
regards
from pointr.
Related Issues (20)
- How to use pre-trained models? HOT 4
- Pretrained AdaPoinTr models HOT 3
- The question about the code of GRNet in this repository. HOT 2
- No module named 'PoinTr' found HOT 1
- 大佬你好,注意到你的shapenet2pc只有采样到8192分辨率,那残缺点云是如何制作的呢
- Training error: ModuleNotFoundError: No module named 'pointnet2_ops' HOT 2
- Question about the query ranking.
- Training PoinTr on Custom Dataset HOT 4
- How to get the FLOPs and Throughput like table.9 in the paper?
- 测试完PCN数据集只输出了一个log HOT 3
- Some questions about KITTI
- In KITTI test, the generated point cloud is not base on input HOT 3
- Works on CUDA11.1 but not on CUDA11.8 HOT 1
- 训练权重
- SSC code
- 2 errors detected in the compilation of "gridding.cu"
- How the foreground region is determined for downstream object detection tasks
- 有关训练出来的数据集的问题 HOT 1
- 关于自制kitti数据集训练的问题
- 使用预训练模型PCN
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 pointr.