Research map / Image generation / Editing and style transfer
IRCasDiff: Two-Stage Cascaded Diffusion for Compound Infrared Face Reconstruction
Zhiyuan Xia, Haojie Li, Yiguo Qiao, Cunjian Chen
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 IRCasDiff, a two-stage cascaded diffusion model that decomposes compound infrared face degradation and the infrared-to-visible domain gap into sequential subproblems for face reconstruction.
Problem
Real-world thermal infrared face reconstruction must handle compound sensor-specific degradations together with a large infrared-to-visible domain gap, which existing methods handle only under oversimplified or single-degradation assumptions.
Approach
Decomposes the compound problem into two sequential stages handled by cascaded diffusion models, so that sensor noise and cross-modal translation are addressed explicitly rather than with simplified degradation assumptions.
Closest papers by meaning
- Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restoration (NeurIPS 2025 · similarity 0.84)
- Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark (NeurIPS 2025 · similarity 0.84)
- DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution (CVPR 2025 · similarity 0.84)
- $InterLCM$: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration (ICLR 2025 · similarity 0.84)
- A Modular Conditional Diffusion Framework for Image Reconstruction (NeurIPS 2024 · similarity 0.84)
- WaveFace: Authentic Face Restoration with Efficient Frequency Recovery (CVPR 2024 · similarity 0.83)
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.
