Beyond Image Prior: Embedding Noise Prior into Latent Space of Conditional Denoising Transformer
International Journal of Computer Vision · 2025-11 · 133 (11) · 7591-7611
DOI: 10.1007/s11263-025-02553-w ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 06.08.2025. Verfasst von Yuanfei Huang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 78 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Existing learning-based denoising methods typically train models to generalize the image prior from large-scale datasets, suffering from the variability in noise distributions encountered in real-world scenarios. In this work, we propose a new perspective on the denoising challenge by highlighting the distinct separation between noise and image priors. This insight forms the basis for our development of conditional optimization framework, designed to overcome the constraints of traditional denoising framework. To this end, we introduce a Locally Noise Prior Estimation (LoNPE) algorithm, which accurately estimates the noise prior directly from a single raw noisy image. This estimation acts as an explicit prior representation of the camera sensor’s imaging environment, distinct from the image prior of scenes. Additionally, we design an auxiliary learnable LoNPE network tailored for practical application to sRGB noisy images. Leveraging the estimated noise prior, we present a novel Conditional Denoising Transformer (Condformer), by incorporating the noise prior into a conditional self-attention mechanism. This integration allows the Condformer to segment the optimization process into multiple explicit subspaces, significantly enhancing the model’s generalization and flexibility. Extensive experimental evaluations on both synthetic and real-world datasets, demonstrate that the proposed method achieves superior performance over current state-of-the-art methods. The source code is available at https://github.com/BNU-ERC-ITEA/Condformer.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Huang, Y., & Huang, H. (2025). Beyond Image Prior: Embedding Noise Prior into Latent Space of Conditional Denoising Transformer. International Journal of Computer Vision, 133(11), 7591-7611. https://doi.org/10.1007/s11263-025-02553-w
Vancouver
Huang Y, Huang H. Beyond Image Prior: Embedding Noise Prior into Latent Space of Conditional Denoising Transformer. International Journal of Computer Vision. 2025;133(11):7591-7611. doi:10.1007/s11263-025-02553-w
BibTeX
@article{Huang2025,
author = {Huang, Yuanfei and Huang, Hua},
title = {Beyond Image Prior: Embedding Noise Prior into Latent Space of Conditional Denoising Transformer},
journal = {International Journal of Computer Vision},
year = {2025},
volume = {133},
number = {11},
pages = {7591--7611},
doi = {10.1007/s11263-025-02553-w}
}
EUVIMED