Open daxiongpro opened 3 years ago
@happinesslz
Hi thanks for your work. I have similar questions on the code of 'fusion' module.
How did you make the 'correspondence' and the 'Point-wise Image Feature'. Could u explain some codes of this part.
Thanks
Hi @happinesslz ! Thanks for the great work.
I join the question about the fusion part. As I understood, the main correspondence happens with grid_sample
call where point cloud coordinates represented in normalized form [-1; 1]. But I have doubts if these coordinates can be directly mapped to image feature maps except the original image with projection matrix. How this mapping works?
Speaking about this code:
def Feature_Gather(feature_map, xy):
"""
:param xy:(B,N,2) normalize to [-1,1]
:param feature_map:(B,C,H,W)
:return:
"""
# use grid_sample for this.
# xy(B,N,2)->(B,1,N,2)
xy = xy.unsqueeze(1)
interpolate_feature = grid_sample(feature_map, xy) # (B,C,1,N)
return interpolate_feature.squeeze(2) # (B,C,N)
How can we be sure that coordinates xy
mapped to feature_map correctly? I have these question because CNN layers have produce images with different sizes
Hello, I find your code "
class Fusion_Conv
" concactpoint_features
andimg_features
directly. Where is your "w" part in your code?