Deblurring via Stochastic Refinement
원문 초록
Image deblurring is an ill-posed problem with multiple plausible solutions for a given input image. However, most existing methods produce a deterministic estimate of the clean image and are trained to minimize pixel-level distortion. These metrics are known to be poorly correlated with human perception, and often lead to unrealistic reconstructions. We present an alternative framework for blind deblurring based on conditional diffusion models. Unlike existing techniques, we train a stochastic sampler that refines the output of a deterministic predictor and is capable of producing a diverse set of plausible reconstructions for a given input. This leads to a significant improvement in perceptual quality over existing state-of-the-art methods across multiple standard benchmarks. Our predict-and-refine approach also enables much more efficient sampling compared to typical diffusion models. Combined with a carefully tuned network architecture and inference procedure, our method is competitive in terms of distortion metrics such as PSNR. These results show clear benefits of our diffusion-based method for deblurring and challenge the widely used strategy of producing a single, deterministic reconstruction.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Efficient RAW Image Deblurring with Adaptive Frequency Modulation
NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results
X-DECODE: EXtreme Deblurring with Curriculum Optimization and Domain Equalization
One-Step Diffusion Model for Image Motion-Deblurring
DarkDeblur: Learning single-shot image deblurring in low-light condition
Spatial and Frequency Domain Adaptive Fusion Network for Image Deblurring
토론
이 논문과 연결된 포럼 글이 아직 없습니다.