Research map / Vision-language and multimodal / Cross-modal learning
A Hybrid Space Model for Misaligned Multi-modality Image Fusion
Yi Xiao, Jia Wang, Zhu Liu, Di Wang, Jinyuan Liu, Risheng Liu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add HCCLO contrastive optimization to hyperbolic features (ablation) | HMMF (hyperbolic branch only) · RoadScene | NCC: 0.9048 -> 0.9175 | Improved |
| add HCCLO contrastive optimization to hyperbolic features (ablation) | HMMF (hyperbolic branch only) · RoadScene | MI: 1.9615 -> 2.0672 | Improved |
| add HCCLO (ablation) | HMMF (hyperbolic branch only) · RoadScene | Qabf: 0.2251 -> 0.2278 | No clear effect |
| fuse Euclidean and hyperbolic features with TDFF instead of Euclidean only (ablation) | HMMF · RoadScene | NCC: 0.9020 -> 0.9491 | Improved |
| fuse Euclidean and hyperbolic features with TDFF instead of Euclidean only (ablation) | HMMF · RoadScene | Qabf: 0.2363 -> 0.5318 | Improved |
| add hyperbolic branch with HCCLO and TDFF to Euclidean features (ablation) | HMMF · RoadScene | MI: 1.8750 -> 2.1767 | Improved |
| use HMMF vs best registration baseline on TNO MI | HMMF · TNO registration | MI: 2.2456 -> 2.1166 | Hurt |
| use HMMF vs IMF on RoadScene registration NCC | HMMF · RoadScene registration | NCC: 0.9445 -> 0.9538 | Improved |
| use HMMF vs strongest fusion baseline on TNO | HMMF · TNO fusion | VIF: 0.8242 -> 1.0612 | Improved |
Closest papers by meaning
- Text-Driven Fusion for Infrared and Visible Images: Achieving Image Scene Adaptation on Hyperbolic Space (ICML 2026 · similarity 0.89)
- Universal Representation for Real-World Misaligned Infrared-Visible Image Fusion (TPAMI 2026 · similarity 0.89)
- MulFS-CAP: Multimodal Fusion-Supervised Cross-Modality Alignment Perception for Unregistered Infrared-Visible Image Fusion (TPAMI 2025 · similarity 0.87)
- Accept the Modality Gap: An Exploration in the Hyperbolic Space (CVPR 2024 · similarity 0.85)
- Beyond Spatial-Domain Supervision: A Relation Constrained Space for Multi-Modal Image Fusion (NeurIPS 2026 · similarity 0.85)
- Self-Supervised Spatial Correspondence Across Modalities (CVPR 2025 · similarity 0.84)
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.
