Closed xuxiaoxxxx closed 2 years ago
Thank you for your reply
I'm very interested in this paper, and after I read this paper I have some questions. First, how can we iterate to update query embedding q(mentioned in 3.3)? Second, after we get the image features, how can we use it? concatenate with previous one? I would appreciate it if you could draw a simple network framework, I think it will help me understand this paper better.
I'm very interested in this paper, and after I read this paper I have some questions. First, how can we iterate to update query embedding q(mentioned in 3.3)? Second, after we get the image features, how can we use it? concatenate with previous one? I would appreciate it if you could draw a simple network framework, I think it will help me understand this paper better.
Sorry for the late reply. The query embedding $q$ are updated by sampling the 2D image features with the 2D-to-3D Feature Transformation. As for the second question, the image features are used to form the BEV representation and estimate the height of each query.
HI, I also interested in your work. According to your description, I draw a simple network framework. Can you help me check if it is correct?
HI, I also interested in your work. According to your description, I draw a simple network framework. Can you help me check if it is correct?
Yes, it is almost right except for missing the Ring Convolution after the transformation and iterating the whole process several times.
I get it, thank you for your reply!