iconLogo
Published:2025/12/3 17:10:44

最強ギャルも納得!画像ぼかしを消す魔法🪄✨

1. 超要約 写真のブレをAIで消す「BlurDM」爆誕!🌟

2. ギャル的キラキラポイント✨

  • ● 拡散モデル(かくさんモデル)っていう、画像をキレイにする最新技術を使ってるんだって!😳
  • ● ブレ(ぼかし)の仕組みをAIが理解して、消し去るからすごい!✨
  • ● 写真アプリとか、色んなとこで役立つ未来が楽しみ~🥰

3. 詳細解説

続きは「らくらく論文」アプリで

BlurDM: A Blur Diffusion Model for Image Deblurring

Jin-Ting He / Fu-Jen Tsai / Yan-Tsung Peng / Min-Hung Chen / Chia-Wen Lin / Yen-Yu Lin

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.

cs / cs.CV / cs.AI