search

WangYueFt / dgcnn

MIT License
1.65k stars 426 forks source link

Semantic segmentation: Result of 4D input is worse than 3D input #61

Open MCLYang opened 4 years ago

MCLYang commented 4 years ago

@WangYueFt @AnTao97 I am using DGCNN for semantic segmentation task for lidar pointcloud. Base on my result I found that the if I only take XYZ as input, the result is significantly better than XYZ+intensity(intensity is a scalar, kinda feature of ray reflection). I want to discuss why 3D is better than 4D for dgcnn? Here are my thoughts and I hope you could give me some advice.

1.For knn, I pass only normalized XYZ to compute the distance. Should I pass XYZ + intensity to compute KNN?

  1. For K value I use the default of the code which is 20, should I adjust the K value?
  2. Any other suggestions will be very appreciated.

Notes that I believe the intensity of Lidar is not dummy variable. Based on my observation, I also tried other model such as pointnet, pointnet++ etc. All the model have better performance if I pass 4D input.

vitakk98 commented 1 year ago

Excuse me, how about XYZI's improvement on semantic segmentation? Did you try? How do I modify the source code?