Enhancing and Learning Denoiser without Clean Reference
This addresses a practical issue for real-world photography applications by improving denoising without needing clean data, though it appears incremental as it builds on existing unsupervised approaches.
The paper tackles the problem of poor generalization in deep image denoising when trained on synthetic noise, by proposing a method that learns noise transference from corrupted samples without clean references, achieving promising performance on real-world benchmarks.
Recent studies on learning-based image denoising have achieved promising performance on various noise reduction tasks. Most of these deep denoisers are trained either under the supervision of clean references, or unsupervised on synthetic noise. The assumption with the synthetic noise leads to poor generalization when facing real photographs. To address this issue, we propose a novel deep image-denoising method by regarding the noise reduction task as a special case of the noise transference task. Learning noise transference enables the network to acquire the denoising ability by observing the corrupted samples. The results on real-world denoising benchmarks demonstrate that our proposed method achieves promising performance on removing realistic noises, making it a potential solution to practical noise reduction problems.