AI Paper Atlas

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

NeurIPS 2026 · Image generation › Editing and style transfer · approach: Diffusion face generation and editing

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

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