search

ZFTurbo / Weighted-Boxes-Fusion

Set of methods to ensemble boxes from different object detection models, including implementation of "Weighted boxes fusion (WBF)" method.
MIT License
1.72k stars 238 forks source link

does the 3d wbf support rotation? #24

Open JianWu313 opened 3 years ago

JianWu313 commented 3 years ago

most of the 3d object-detector need to predict a heading angle(yaw angle),but is seems that the 3d wbf don't use it and another problem is the normalization,.by 2D case it is quite easy because we just need to divided by width and height, but 3D detection are the coordinate in real world with respect to camera coordinate(not just image plane)

ZFTurbo commented 3 years ago

3D WBF only supports rectangular parallelepipeds as input, given as 2 opposite corners (x1, y1, z1) and (x2, y2, z2). If you can convert your 3D boxes in this format you are good.

JianWu313 commented 3 years ago

@ZFTurbo thanks for your quick reply ,I still not so sure why we need to normalize all the coordinate

ZFTurbo commented 3 years ago

Actually algorithm will work without normalization (in this case you need to remove checks and sligtly remade IoU calculation). But anyway it will require rectangular parallelepipeds as input.

JianWu313 commented 3 years ago

@ZFTurbo thanks a lot, I still have one more question about the parameter"weights". Is it used to change the orginial score in each models,for example,w1s1, w2s2, if we have many models ,can we just set all the weights to be 1 (I have found the weights in your paper but don't understand the usage)

ZFTurbo commented 3 years ago

Weights needed to say which model predictions are more important. By default all weights equal to 1.

bringBackm commented 3 years ago

Is there any implementation of yaw angle fusion in 3d boxes...?

TianhaoFu commented 2 years ago

Is there any implementation of yaw angle fusion in 3d boxes...?

Hello, did you find a solution? thanks @bringBackm

TianhaoFu commented 2 years ago

@ZFTurbo thanks a lot, I still have one more question about the parameter"weights". Is it used to change the orginial score in each models,for example,w1_s1, w2_s2, if we have many models ,can we just set all the weights to be 1 (I have found the weights in your paper but don't understand the usage)

Hello, did you find a solution? thanks @JianWu313