[PyTorch] Official implementation of CVPR2022 paper "TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers". https://arxiv.org/abs/2203.11496
Apache License 2.0
613
stars
76
forks
source link
Initialisation of `gaussian_mask` in `TransFusionHead.forward_single` is not consistent with paper. #94
In the original TransFusion paper: it states that the Gaussian Mask, $M$, is initialised as follows, with inspiration from CenterNet:
$$ M_{ij}=\exp(-\frac{(i-c_x)^2 + (j-c_y)^2}{\sigma r^2}) $$
However, upon inspection of the code in
transfusion_head.py
, the following is found :which is equivalent to:
$$ M_{ij}=\exp(-\frac{(i-c_x)^2 + (j-c_y)^2}{2\sigma^2}) $$
as per Objects as Points, which initialises $\sigma$ as per CornerNet.