MMSFormer: Multimodal Transformer for Material and Semantic Segmentation

arXiv:2309.04001v4 Announce Type: replace-cross
Abstract: Leveraging information across diverse modalities is known to enhance performance on multimodal segmentation tasks. However, effectively fusing information from different modalities remains challenging due to the unique characteristics of each modality. In this paper, we propose a novel fusion strategy that can effectively fuse information from different modality combinations. We also propose a new model named Multi-Modal Segmentation TransFormer (MMSFormer) that incorporates the proposed fusion strategy to perform multimodal material and semantic segmentation tasks. MMSFormer …

arxiv cs.cv cs.lg material multimodal segmentation semantic transformer type