Score: 3

BlurDM: A Blur Diffusion Model for Image Deblurring

Published: December 3, 2025 | arXiv ID: 2512.03979v1

By: Jin-Ting He , Fu-Jen Tsai , Yan-Tsung Peng and more

BigTech Affiliations: NVIDIA

Potential Business Impact:

Fixes blurry pictures by reversing how they got blurry.

Business Areas:
Simulation Software

Diffusion models show promise for dynamic scene deblurring; however, existing studies often fail to leverage the intrinsic nature of the blurring process within diffusion models, limiting their full potential. To address it, we present a Blur Diffusion Model (BlurDM), which seamlessly integrates the blur formation process into diffusion for image deblurring. Observing that motion blur stems from continuous exposure, BlurDM implicitly models the blur formation process through a dual-diffusion forward scheme, diffusing both noise and blur onto a sharp image. During the reverse generation process, we derive a dual denoising and deblurring formulation, enabling BlurDM to recover the sharp image by simultaneously denoising and deblurring, given pure Gaussian noise conditioned on the blurred image as input. Additionally, to efficiently integrate BlurDM into deblurring networks, we perform BlurDM in the latent space, forming a flexible prior generation network for deblurring. Extensive experiments demonstrate that BlurDM significantly and consistently enhances existing deblurring methods on four benchmark datasets. The source code is available at https://github.com/Jin-Ting-He/BlurDM.

Country of Origin
🇹🇼 🇺🇸 Taiwan, Province of China, United States

Repos / Data Links

Page Count
32 pages

Category
Computer Science:
CV and Pattern Recognition