AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

SiMO: Single-Modality-Operable Multimodal Collaborative Perception

Jiageng Wen, Shengjie Zhao, Bing Li, Jiafeng Huang, Kenan Ye, Hao Deng

ICLR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add RD fine-tuning (ablation)SiMO-PF · OPV2V-H, LiDAR-onlyAP@70: 0.26 -> 0.94Improved
add RD fine-tuning (ablation)SiMO-PF · OPV2V-H, camera-onlyAP@70: 0 -> 0.45Improved
add LAMMA fusion in place of BEVFusion fusion (both with RD) (ablation)SiMO-PF · OPV2V-H, LiDAR-onlyAP@70: 0.72 -> 0.94Improved
add LAMMA fusion in place of BEVFusion fusion (both with RD) (ablation)SiMO-PF · OPV2V-H, camera-onlyAP@70: 0 -> 0.45Improved
add Pretrain-Align-Fuse learning strategy instead of naive joint training (ablation)SiMO-PF · OPV2V-H, LiDAR-onlyAP@70: 0.01 -> 0.26Improved
add RD fine-tuning to naive joint training (ablation)SiMO-PF naive · OPV2V-H, L+CAP@70: 0.94 -> 0.11Hurt
add LAMMA alignment (ablation)SiMO · Procrustes disparity cam vs lidardisparity: 0.6747 -> 0.0472Improved
add LAMMA alignment (ablation)SiMO · Procrustes disparity cam vs fuseddisparity: 0.3886 -> 0.0215Improved
add SiMO-AF training to AttFusion, camera-onlySiMO-AF vs AttFusion · OPV2V-H, camera-onlyAP@70: 25.30 -> 22.59No clear effect
use SiMO-PF instead of Pyramid Fusion for camera-onlySiMO-PF vs HEAL · OPV2V-H, camera-onlyAP@30: 68.45 -> 80.81Improved
use SiMO-PF instead of HEAL under heterogeneous failure, camera egoSiMO-PF vs HEAL · OPV2V-H, C-egoAP@70: 0.72 -> 0.70No clear effect
use SiMO-PF instead of HEAL under heterogeneous failure, camera egoSiMO-PF vs HEAL · OPV2V-H, C-egoAP@30: 0.85 -> 0.89Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy