Unicorn: Unified Neural Image Compression with One Number Reconstruction

• URL: http://arxiv.org/abs/2412.08210v1
• Date: Wed, 11 Dec 2024 08:59:04 GMT
• Title: Unicorn: Unified Neural Image Compression with One Number Reconstruction
• Authors: Qi Zheng, Haozhi Wang, Zihao Liu, Jiaming Liu, Peiye Liu, Zhijian Hao, Yanheng Lu, Dimin Niu, Jinjia Zhou, Minge Jing, Yibo Fan,
• Abstract summary: We propose an innovative paradigm, which we dub textbfUnicorn (textbfUnified textbfNeural textbfImage textbfCompression with textbfOne textbfNnumber textbfReconstruction)<n>By conceptualizing the images as index-image pairs and learning the inherent distribution of pairs in a subtle neural network, Unicorn can reconstruct a visually pleasing image from a randomly generated noise with only one index number.
• Score: 25.79670851851377
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Prevalent lossy image compression schemes can be divided into: 1) explicit image compression (EIC), including traditional standards and neural end-to-end algorithms; 2) implicit image compression (IIC) based on implicit neural representations (INR). The former is encountering impasses of either leveling off bitrate reduction at a cost of tremendous complexity while the latter suffers from excessive smoothing quality as well as lengthy decoder models. In this paper, we propose an innovative paradigm, which we dub \textbf{Unicorn} (\textbf{U}nified \textbf{N}eural \textbf{I}mage \textbf{C}ompression with \textbf{O}ne \textbf{N}number \textbf{R}econstruction). By conceptualizing the images as index-image pairs and learning the inherent distribution of pairs in a subtle neural network model, Unicorn can reconstruct a visually pleasing image from a randomly generated noise with only one index number. The neural model serves as the unified decoder of images while the noises and indexes corresponds to explicit representations. As a proof of concept, we propose an effective and efficient prototype of Unicorn based on latent diffusion models with tailored model designs. Quantitive and qualitative experimental results demonstrate that our prototype achieves significant bitrates reduction compared with EIC and IIC algorithms. More impressively, benefitting from the unified decoder, our compression ratio escalates as the quantity of images increases. We envision that more advanced model designs will endow Unicorn with greater potential in image compression. We will release our codes in \url{https://github.com/uniqzheng/Unicorn-Laduree}.

Related papers

• Zero-shot denoising via neural compression: Theoretical and algorithmic framework [10.063403779232072]
  We propose the Zero-Shot Neural Compression Denoiser (ZS-NCD), a novel denoising framework based on neural compression.<n>ZS-NCD treats a neural compression network as an untrained model, optimized directly on patches extracted from a single noisy image.<n>We show that ZS-NCD achieves state-of-the-art performance among zero-shot denoisers for both Gaussian and Poisson noise.
  arXiv  Detail & Related papers  (2025-06-15T02:29:32Z)
• Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression [90.59962443790593]
  In this paper, we present a variable-rate image compression model based on invertible transform to overcome limitations. Specifically, we design a lightweight multi-scale invertible neural network, which maps the input image into multi-scale latent representations. Experimental results demonstrate that the proposed method achieves state-of-the-art performance compared to existing variable-rate methods.
  arXiv  Detail & Related papers  (2025-03-27T09:08:39Z)
• Map-Assisted Remote-Sensing Image Compression at Extremely Low Bitrates [47.47031054057152]
  Generative models have been explored to compress RS images into extremely low-bitrate streams. These generative models struggle to reconstruct visually plausible images due to the highly ill-posed nature of extremely low-bitrate image compression. We propose an image compression framework that utilizes a pre-trained diffusion model with powerful natural image priors to achieve high-realism reconstructions.
  arXiv  Detail & Related papers  (2024-09-03T14:29:54Z)
• FCNR: Fast Compressive Neural Representation of Visualization Images [6.648837287947374]
  We present FCNR, a fast compressive neural representation for tens of thousands of visualization images. Built on the recent advances in stereo image compression, FCNR assimilates stereo context modules and joint context transfer modules to compress image pairs.
  arXiv  Detail & Related papers  (2024-07-23T10:34:02Z)
• Lossy Image Compression with Conditional Diffusion Models [25.158390422252097]
  This paper outlines an end-to-end optimized lossy image compression framework using diffusion generative models. In contrast to VAE-based neural compression, where the (mean) decoder is a deterministic neural network, our decoder is a conditional diffusion model. Our approach yields stronger reported FID scores than the GAN-based model, while also yielding competitive performance with VAE-based models in several distortion metrics.
  arXiv  Detail & Related papers  (2022-09-14T21:53:27Z)
• Lossy Image Compression with Quantized Hierarchical VAEs [33.173021636656465]
  ResNet VAEs are originally designed for data (image) distribution modeling. We present a powerful and efficient model that outperforms previous methods on natural image lossy compression. Our model compresses images in a coarse-to-fine fashion and supports parallel encoding and decoding.
  arXiv  Detail & Related papers  (2022-08-27T17:15:38Z)
• Estimating the Resize Parameter in End-to-end Learned Image Compression [50.20567320015102]
  We describe a search-free resizing framework that can further improve the rate-distortion tradeoff of recent learned image compression models. Our results show that our new resizing parameter estimation framework can provide Bjontegaard-Delta rate (BD-rate) improvement of about 10% against leading perceptual quality engines.
  arXiv  Detail & Related papers  (2022-04-26T01:35:02Z)
• The Devil Is in the Details: Window-based Attention for Image Compression [58.1577742463617]
  Most existing learned image compression models are based on Convolutional Neural Networks (CNNs) In this paper, we study the effects of multiple kinds of attention mechanisms for local features learning, then introduce a more straightforward yet effective window-based local attention block. The proposed window-based attention is very flexible which could work as a plug-and-play component to enhance CNN and Transformer models.
  arXiv  Detail & Related papers  (2022-03-16T07:55:49Z)
• Reducing Redundancy in the Bottleneck Representation of the Autoencoders [98.78384185493624]
  Autoencoders are a type of unsupervised neural networks, which can be used to solve various tasks. We propose a scheme to explicitly penalize feature redundancies in the bottleneck representation. We tested our approach across different tasks: dimensionality reduction using three different dataset, image compression using the MNIST dataset, and image denoising using fashion MNIST.
  arXiv  Detail & Related papers  (2022-02-09T18:48:02Z)
• Implicit Neural Representations for Image Compression [103.78615661013623]
  Implicit Neural Representations (INRs) have gained attention as a novel and effective representation for various data types. We propose the first comprehensive compression pipeline based on INRs including quantization, quantization-aware retraining and entropy coding. We find that our approach to source compression with INRs vastly outperforms similar prior work.
  arXiv  Detail & Related papers  (2021-12-08T13:02:53Z)
• Countering Adversarial Examples: Combining Input Transformation and Noisy Training [15.561916630351947]
  adversarial examples pose a threat to security-sensitive image recognition task. Traditional JPEG compression is insufficient to defend those attacks but can cause an abrupt accuracy decline to benign images. We make modifications to traditional JPEG compression algorithm which becomes more favorable for NN.
  arXiv  Detail & Related papers  (2021-06-25T02:46:52Z)
• Pyramid Attention Networks for Image Restoration [124.34970277136061]
  Self-similarity refers to the image prior widely used in image restoration algorithms. Recent advanced deep convolutional neural network based methods for image restoration do not take full advantage of self-similarities. We present a novel Pyramid Attention module for image restoration, which captures long-range feature correspondences from a multi-scale feature pyramid.
  arXiv  Detail & Related papers  (2020-04-28T21:12:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.