Enhanced Denoising and Convergent Regularisation Using Tweedie Scaling
원문 초록
The inherent ill-posed nature of image reconstruction problems, due to limitations in the physical acquisition process, is typically addressed by introducing a regularisation term that incorporates prior knowledge about the underlying image. The iterative framework of Plug-and-Play methods, specifically designed for tackling such inverse problems, achieves state-of-the-art performance by replacing the regularisation with a generic denoiser, which may be parametrised by a neural network architecture. However, these deep learning approaches suffer from a critical limitation: the absence of a control parameter to modulate the regularisation strength, which complicates the design of a convergent regularisation. To address this issue, this work introduces a novel scaling method that explicitly integrates and adjusts the strength of regularisation. The scaling parameter enhances interpretability by reflecting the quality of the denoiser's learning process, and also systematically improves its optimisation. Furthermore, the proposed approach ensures that the resulting family of regularisations is provably stable and convergent.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
LangMamba: A Language-driven Mamba Framework for Low-dose CT Denoising with Vision-language Models
Imaging at the quantum limit with convolutional neural networks
LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter
Deep Spectral Prior
Color Image Restoration Exploiting Inter-channel Correlation with a 3-stage CNN
Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.