A multi-layer image representation using Regularized Residual Quantization: application to compression and denoising
A learning-based framework for representation of domain-specific images is proposed where joint compression and denoising can be done using a VQ-based multi-layer network. While it learns to compress the images from a training set, the compression performance is very well generalized on images from a test set. Moreover, when fed with noisy versions of the test set, since it has priors from clean images, the network also efficiently denoises the test images during the reconstruction. The proposed framework is a regularized version of the Residual Quantization (RQ) where at each stage, the quantization error from the previous stage is further quantized. Instead of codebook learning from the k-means which over-trains for high-dimensional vectors, we show that only generating the codewords from a random, but properly regularized distribution suffices to compress the images globally and without the need to resort to patch-based division of images. The experiments are done on the \textit{CroppedYale-B} set of facial images and the method is compared with the JPEG-2000 codec for compression and BM3D for denoising, showing promising results.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingQuantizationSimilar Papers 제목 키워드 기반
Regularized Residual Quantization: a multi-layer sparse dictionary learning approach
The Residual Quantization (RQ) framework is revisited where the quantization distortion is being successively reduced in multi-layers. Inspired by the reverse-water-filling paradigm in rate-distortion theory, an efficien…
Dictionary LearningQuantizationSuper-ResolutionRegularized Robust Coding for Face Recognition
Recently the sparse representation based classification (SRC) has been proposed for robust face recognition (FR). In SRC, the testing image is coded as a sparse linear combination of the training samples, and the represe…
Face RecognitionRobust Face RecognitionSparse Representation-based ClassificationSeqLoRA: Bilevel Orthogonal Adaptation for Continual Multi-Concept Generation
Parameter-efficient fine-tuning enables fast personalization of text-to-image diffusion models, but composing multiple custom concepts remains challenging due to representation interference. Existing modular methods eith…
parameter-efficient fine-tuningBilevel OptimizationContinual LearningImage GenerationTransEM:Residual Swin-Transformer based regularized PET image reconstruction
Positron emission tomography(PET) image reconstruction is an ill-posed inverse problem and suffers from high level of noise due to limited counts received. Recently deep neural networks especially convolutional neural ne…
Image ReconstructionNeural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers
The empirical emergence of neural collapse -- a surprising symmetry in the feature representations of the training data in the penultimate layer of deep neural networks -- has spurred a line of theoretical research aimed…