Research map / Image generation / Super-resolution
CoVisIT: Cross-modal Prior Guided Diffusion Model for Visible-to-Infrared Image Translation
Linfeng Tang, Tong Hu, Zizhuo Li, Hao Zhang, Han Xu, Zhenfeng Shao, Jiayi Ma
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes CoVisIT, a cross-modal prior guided diffusion model for translating visible images to infrared images.
Problem
Acquiring high-resolution infrared images is hard due to sensor limits and cost, and pixel-aligned visible-infrared pairs are difficult to collect for visible-to-infrared translation.
Approach
Uses cross-modal priors to guide a diffusion model for visible-to-infrared translation so that paired data is not required; the abstract is truncated so details beyond this are unknown.
Closest papers by meaning
- D3F-IR: Dual-Domain Deterministic Flow Matching for Visible-to-Infrared Translation (ECCV 2026 · similarity 0.89)
- TherA: Thermal-Aware Visual-Language Prompting for Controllable RGB-to-Thermal Infrared Translation (CVPR 2026 · similarity 0.89)
- Taming Generative Diffusion Model for Task-Oriented Infrared Imaging (CVPR 2026 · similarity 0.89)
- SynthRGB-T: Language-Vision Guided Image Translation for Diversity Synthesis (CVPR 2026 · similarity 0.87)
- DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution (CVPR 2025 · similarity 0.86)
- Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark (NeurIPS 2025 · similarity 0.86)
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.
