Research map / Vision-language and multimodal / Cross-modal learning
ControlFuse: Instruction-guided Multi-Granularity Controllable Image Fusion
Libo Zhao, Xiaoli Zhang, Zeyu Wang
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 FMC and CGI together to baseline (ablation) | ControlFuse · MSRS | SD: 34.22 -> 61.15 | Improved |
| add FMC alone to baseline (ablation) | ControlFuse · MSRS | SD: 34.22 -> 39.15 | Improved |
| add CGI alone to baseline (ablation) | ControlFuse · MSRS | SD: 34.22 -> 36.83 | Improved |
| add object localization loss Lm (ablation) | ControlFuse · MSRS | SD: 40.21 -> 61.15 | Improved |
| add content fidelity loss Lf (ablation) | ControlFuse · MSRS | SD: 37.43 -> 61.15 | Improved |
| add curvature alignment loss La (ablation) | ControlFuse · MSRS | SD: 39.82 -> 61.15 | Improved |
| add negative prompts in curvature-aware contrastive learning (ablation) | ControlFuse · segmentation IoU/F1 | IoU/F1 | Improved |
| use semantic-level instead of global instruction | ControlFuse · M3FD detection | mAP@.5: 0.715 -> 0.773 | Improved |
| use semantic-level instead of global instruction | ControlFuse · MSRS segmentation | mIoU: 0.489 -> 0.496 | Improved |
| ControlFuse-Global vs MTG-Fusion on MSRS | MTG-Fusion · MSRS | SD: 61.44 (MTG) vs 61.15 (ours); EN 5.98 vs 5.99 | Mixed |
Closest papers by meaning
- ControlFusion: A Controllable Image Fusion Network with Language-Vision Degradation Prompts (NeurIPS 2025 · similarity 0.85)
- Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion Model (NeurIPS 2024 · similarity 0.85)
- One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion (CVPR 2025 · similarity 0.85)
- LLaVA-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models (ICLR 2025 · similarity 0.85)
- Beyond Spatial-Domain Supervision: A Relation Constrained Space for Multi-Modal Image Fusion (NeurIPS 2026 · similarity 0.84)
- Robust Fusion Controller: Degradation-Aware Image Fusion with Fine-Grained Language Instructions (AAAI 2026 · 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.
