TransFusion: Multi-modal Fusion Network for Semantic Segmentation
This repo contains the official implementation for the CVPR2023 photogrammetric workshop paper: TransFusion. Proposed model 2D for semantic segmentation that fuses images directly with point clouds without the need for lossy pre-processing of the point clouds.
Citation
@InProceedings{Maiti_2023_CVPR,
author = {Maiti, Abhisek and Elberink, Sander Oude and Vosselman, George},
title = {TransFusion: Multi-Modal Fusion Network for Semantic Segmentation},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2023},
pages = {6536-6546}
}