SiMO: Single-Modality-Operable Multimodal Collaborative Perception

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wen, Jiageng, Zhao, Shengjie, Li, Bing, Huang, Jiafeng, Ye, Kenan, Deng, Hao
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908873441411072
author Wen, Jiageng
Zhao, Shengjie
Li, Bing
Huang, Jiafeng
Ye, Kenan
Deng, Hao
author_facet Wen, Jiageng
Zhao, Shengjie
Li, Bing
Huang, Jiafeng
Ye, Kenan
Deng, Hao
contents Collaborative perception integrates multi-agent perspectives to enhance the sensing range and overcome occlusion issues. While existing multimodal approaches leverage complementary sensors to improve performance, they are highly prone to failure--especially when a key sensor like LiDAR is unavailable. The root cause is that feature fusion leads to semantic mismatches between single-modality features and the downstream modules. This paper addresses this challenge for the first time in the field of collaborative perception, introducing Single-Modality-Operable Multimodal Collaborative Perception (SiMO). By adopting the proposed Length-Adaptive Multi-Modal Fusion (LAMMA), SiMO can adaptively handle remaining modal features during modal failures while maintaining consistency of the semantic space. Additionally, leveraging the innovative "Pretrain-Align-Fuse-RD" training strategy, SiMO addresses the issue of modality competition--generally overlooked by existing methods--ensuring the independence of each individual modality branch. Experiments demonstrate that SiMO effectively aligns multimodal features while simultaneously preserving modality-specific features, enabling it to maintain optimal performance across all individual modalities. The implementation details can be found in https://github.com/dempsey-wen/SiMO.
format Preprint
id arxiv_https___arxiv_org_abs_2603_08240
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SiMO: Single-Modality-Operable Multimodal Collaborative Perception
Wen, Jiageng
Zhao, Shengjie
Li, Bing
Huang, Jiafeng
Ye, Kenan
Deng, Hao
Computer Vision and Pattern Recognition
Collaborative perception integrates multi-agent perspectives to enhance the sensing range and overcome occlusion issues. While existing multimodal approaches leverage complementary sensors to improve performance, they are highly prone to failure--especially when a key sensor like LiDAR is unavailable. The root cause is that feature fusion leads to semantic mismatches between single-modality features and the downstream modules. This paper addresses this challenge for the first time in the field of collaborative perception, introducing Single-Modality-Operable Multimodal Collaborative Perception (SiMO). By adopting the proposed Length-Adaptive Multi-Modal Fusion (LAMMA), SiMO can adaptively handle remaining modal features during modal failures while maintaining consistency of the semantic space. Additionally, leveraging the innovative "Pretrain-Align-Fuse-RD" training strategy, SiMO addresses the issue of modality competition--generally overlooked by existing methods--ensuring the independence of each individual modality branch. Experiments demonstrate that SiMO effectively aligns multimodal features while simultaneously preserving modality-specific features, enabling it to maintain optimal performance across all individual modalities. The implementation details can be found in https://github.com/dempsey-wen/SiMO.
title SiMO: Single-Modality-Operable Multimodal Collaborative Perception
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.08240