Wide Inference Network for Image Denoising via Learning Pixel-distribution Prior
We explore an innovative strategy for image denoising by using convolutional neural networks (CNN) to learn similar pixel-distribution features from noisy images. Many types of image noise follow a certain pixel-distribution in common, such as additive white Gaussian noise (AWGN). By increasing CNN's width with larger reception fields and more channels in each layer, CNNs can reveal the ability to extract more accurate pixel-distribution features. The key to our approach is a discovery that wider CNNs with more convolutions tend to learn the similar pixel-distribution features, which reveals a new strategy to solve low-level vision problems effectively that the inference mapping primarily relies on the priors behind the noise property instead of deeper CNNs with more stacked nonlinear layers. We evaluate our work, Wide inference Networks (WIN), on AWGN and demonstrate that by learning pixel-distribution features from images, WIN-based network consistently achieves significantly better performance than current state-of-the-art deep CNN-based methods in both quantitative and visual evaluations. \textit{Code and models are available at \url{https://github.com/cswin/WIN}}.
Code (2)
Tasks
DenoisingImage DenoisingSimilar Papers 제목 키워드 기반
Learning Pixel-Distribution Prior with Wider Convolution for Image Denoising
In this work, we explore an innovative strategy for image denoising by using convolutional neural networks (CNN) to learn pixel-distribution from noisy data. By increasing CNN's width with large reception fields and more…
DenoisingImage DenoisingSpectrally-Guided Diffusion Noise Schedules
Denoising diffusion models are widely used for high-quality image and video generation. Their performance depends on noise schedules, which define the distribution of noise levels applied during training and the sequence…
Video GenerationZero-Shot Blind-spot Image Denoising via Implicit Neural Sampling
The blind-spot principle has been a widely used tool in zero-shot image denoising but faces challenges with real-world noise that exhibits strong local correlations. Existing methods focus on reducing noise correlati…
DenoisingImage DenoisingWhere Does Generative Difficulty Reside? An Empirical Study of Target Representations
The target representation defines the distribution an image generator must learn, yet it is often treated as an interchangeable interface. This assumption is particularly questionable for continuous masked generators, wh…
Image Segmentation by Iterative Inference from Conditional Score Estimation
Inspired by the combination of feedforward and iterative computations in the virtual cortex, and taking advantage of the ability of denoising autoencoders to estimate the score of a joint distribution, we propose a novel…
DenoisingImage SegmentationSemantic Segmentation