A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf
.
Filters
Tensorformer: Normalized Matrix Attention Transformer for High-quality Point Cloud Reconstruction
[article]
2023
arXiv
pre-print
We introduce a novel normalized matrix attention transformer (Tensorformer) to perform high-quality reconstruction. ...
The proposed matrix attention allows for simultaneous point-wise and channel-wise message passing, while the previous vector attention loses neighbor point information across different channels. ...
CONCLUSION We have presented Tensorformer based on two key mechanisms, matrix attention and weight normalization. We apply it to point cloud reconstruction and achieve high quality result. ...
arXiv:2306.15989v3
fatcat:o3r2grkvqfdoxhdv5yamsknwqe