Adaptive Dynamic Filtering Network for Image Denoising
نویسندگان
چکیده
In image denoising networks, feature scaling is widely used to enlarge the receptive field size and reduce computational costs. This practice, however, also leads loss of high-frequency information fails consider within-scale characteristics. Recently, dynamic convolution has exhibited powerful capabilities in processing (e.g., edges, corners, textures), but previous works lack sufficient spatial contextual filter generation. To alleviate these issues, we propose employ improve learning multi-scale features. Specifically, design a spatially enhanced kernel generation (SEKG) module convolution, enabling context with very low complexity. Based on SEKG module, block (DCB) (MDCB). The former enhances via preserves low-frequency skip connections. latter utilizes shared adaptive kernels idea dilated achieve efficient extraction. proposed multi-dimension integration (MFI) mechanism further fuses features, providing precise contextually enriched representations. Finally, build an network DCB MDCB, named ADFNet. It achieves better performance complexity real-world synthetic Gaussian noisy datasets. source code available at https://github.com/it-hao/ADFNet.
منابع مشابه
An Adaptive Hierarchical Method Based on Wavelet and Adaptive Filtering for MRI Denoising
MRI is one of the most powerful techniques to study the internal structure of the body. MRI image quality is affected by various noises. Noises in MRI are usually thermal and mainly due to the motion of charged particles in the coil. Noise in MRI images also cause a limitation in the study of visual images as well as computer analysis of the images. In this paper, first, it is proved that proba...
متن کاملA Block-Grouping Method for Image Denoising by Block Matching and 3-D Transform Filtering
Image denoising by block matching and threedimensionaltransform filtering (BM3D) is a two steps state-ofthe-art algorithm that uses the redundancy of similar blocks innoisy image for removing noise. Similar blocks which can havesome overlap are found by a block matching method and groupedto make 3-D blocks for 3-D transform filtering. In this paper wepropose a new block grouping algorithm in th...
متن کاملImage Denoising with Unsupervised, Information-Theoretic, Adaptive Filtering
The problem of denoising images is one of the most important and widely studied problems in image processing and computer vision. Various image filtering strategies based on linear systems, statistics, information theory, and variational calculus, have been effective, but invariably make strong assumptions about the properties of the signal and/or noise. Therefore, they lack the generality to b...
متن کاملA New Shearlet Framework for Image Denoising
Traditional noise removal methods like Non-Local Means create spurious boundaries inside regular zones. Visushrink removes too many coefficients and yields recovered images that are overly smoothed. In Bayesshrink method, sharp features are preserved. However, PSNR (Peak Signal-to-Noise Ratio) is considerably low. BLS-GSM generates some discontinuous information during the course of denoising a...
متن کاملAdaptive Probabilistic Wavelet Shrinkage for Image Denoising
We study a Bayesian wavelet shrinkage approach for natural images based on a probability that a given coefficient contains a significant noise-free component, which we call “signal of interest”. First we develop new subband adaptive wavelet shrinkage method of this kind for the generalized Laplacian prior for noise free coefficients. We compare the new shrinkage approach with other subband adap...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence
سال: 2023
ISSN: ['2159-5399', '2374-3468']
DOI: https://doi.org/10.1609/aaai.v37i2.25317