# Multi-Attribute guided Thermal Face Image Translation based on Latent Diffusion Model

arXiv: https://arxiv.org/abs/2512.21032 · HTML: https://mlsanity.com/paper/2512.21032/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 24 Dec 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models](https://mlsanity.com/paper/2205.07680/) (2022)
- [Diffusion-based Image Translation using Disentangled Style and Content Representation](https://mlsanity.com/paper/2209.15264/) (2022)
- [Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control](https://mlsanity.com/paper/2405.12970/) (2024)
- [AT-DDPM: Restoring Faces degraded by Atmospheric Turbulence using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2208.11284/) (2022)
- [A Large-Scale, Time-Synchronized Visible and Thermal Face Dataset](https://mlsanity.com/paper/2101.02637/) (2021)
- [Controllable and Guided Face Synthesis for Unconstrained Face Recognition](https://mlsanity.com/paper/2207.10180/) (2022)
- [SpeakingFaces: A Large-Scale Multimodal Dataset of Voice Commands with Visual and Thermal Video Streams](https://mlsanity.com/paper/2012.02961/) (2020)
- [Polarimetric Thermal to Visible Face Verification via Self-Attention Guided Synthesis](https://mlsanity.com/paper/1904.07344/) (2019)
- [ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning](https://mlsanity.com/paper/2404.15449/) (2024)
- [T2V-DDPM: Thermal to Visible Face Translation using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2209.08814/) (2022)
- [Multi-Scale Thermal to Visible Face Verification via Attribute Guided Synthesis](https://mlsanity.com/paper/2004.09502/) (2020)
- [Thermal to Visible Synthesis of Face Images using Multiple Regions](https://mlsanity.com/paper/1803.07599/) (2018)
- [GP-UNIT: Generative Prior for Versatile Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2306.04636/) (2023)
- [Thermal to Visible Image Synthesis under Atmospheric Turbulence](https://mlsanity.com/paper/2204.03057/) (2022)

## Abstract (arXiv)

Modern surveillance systems increasingly rely on multi-wavelength sensors and deep neural networks to recognize faces in infrared images captured at night. However, most facial recognition models are trained on visible light datasets, leading to substantial performance degradation on infrared inputs due to significant domain shifts. Early feature-based methods for infrared face recognition proved ineffective, prompting researchers to adopt generative approaches that convert infrared images into visible light images for improved recognition. This paradigm, known as Heterogeneous Face Recognition (HFR), faces challenges such as model and modality discrepancies, leading to distortion and feature loss in generated images. To address these limitations, this paper introduces a novel latent diffusion-based model designed to generate high-quality visible face images from thermal inputs while preserving critical identity features. A multi-attribute classifier is incorporated to extract key facial attributes from visible images, mitigating feature loss during infrared-to-visible image restoration. Additionally, we propose the Self-attn Mamba module, which enhances global modeling of cross-modal features and significantly improves inference speed. Experimental results on two benchmark datasets demonstrate the superiority of our approach, achieving state-of-the-art performance in both image quality and identity preservation.