Synonymous Variational Inference for Perceptual Image Compression

• URL: http://arxiv.org/abs/2505.22438v1
• Date: Wed, 28 May 2025 15:03:27 GMT
• Title: Synonymous Variational Inference for Perceptual Image Compression
• Abstract summary: We propose a synonymous variational inference (SVI) method to re-analyze the image compression problem.<n>It takes perceptual similarity as a typical synonymous criterion to build an ideal synonymous set (Synset)<n>We introduce a new image compression scheme that corresponds to the analytical process of SVI.
• Score: 9.694218792074693
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent contributions of semantic information theory reveal the set-element relationship between semantic and syntactic information, represented as synonymous relationships. In this paper, we propose a synonymous variational inference (SVI) method based on this synonymity viewpoint to re-analyze the perceptual image compression problem. It takes perceptual similarity as a typical synonymous criterion to build an ideal synonymous set (Synset), and approximate the posterior of its latent synonymous representation with a parametric density by minimizing a partial semantic KL divergence. This analysis theoretically proves that the optimization direction of perception image compression follows a triple tradeoff that can cover the existing rate-distortion-perception schemes. Additionally, we introduce synonymous image compression (SIC), a new image compression scheme that corresponds to the analytical process of SVI, and implement a progressive SIC codec to fully leverage the model's capabilities. Experimental results demonstrate comparable rate-distortion-perception performance using a single progressive SIC codec, thus verifying the effectiveness of our proposed analysis method.

Related papers

• A Synonymous Variational Perspective on the Rate-Distortion-Perception Tradeoff [13.751084926770773]
  In this paper, motivated by a synonymity-based semantic information perspective, we reformulate reconstruction as recovering any admissible sample within an ideal synonymous set (synset) associated with the source.<n>We show that the distributional divergence term arises naturally from the synset-based reconstruction objective, clarify its compatibility with existing formulations and classical RD theory, and suggest the potential advantages of synonymous source coding.
  arXiv  Detail & Related papers  (2026-04-16T04:21:32Z)
• Higher fidelity perceptual image and video compression with a latent conditioned residual denoising diffusion model [55.2480439325792]
  We propose a hybrid compression scheme optimized for perceptual quality, extending the approach of the CDC model with a decoder network.<n>We achieve up to +2dB PSNR fidelity improvements while maintaining comparable LPIPS and FID perceptual scores when compared with CDC.
  arXiv  Detail & Related papers  (2025-05-19T14:13:14Z)
• Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion [28.61304513668606]
  ResULIC is a residual-guided ultra lowrate image compression system.<n>It incorporates residual signals into both semantic retrieval and the diffusion-based generation process.<n>It achieves superior objective and subjective performance compared to state-of-the-art diffusion-based methods.
  arXiv  Detail & Related papers  (2025-05-13T06:51:23Z)
• Hierarchical Semantic Compression for Consistent Image Semantic Restoration [62.97519327310638]
  We propose a novel hierarchical semantic compression (HSC) framework that purely operates within intrinsic semantic spaces from generative models.<n> Experimental results demonstrate that the proposed HSC framework achieves the state-of-the-art performance on subjective quality and consistency for human vision.
  arXiv  Detail & Related papers  (2025-02-24T03:20:44Z)
• A Rate-Distortion-Classification Approach for Lossy Image Compression [0.0]
  In lossy image compression, the objective is to achieve minimal signal distortion while compressing images to a specified bit rate. To bridge the gap between image compression and visual analysis, we propose a Rate-Distortion-Classification (RDC) model for lossy image compression.
  arXiv  Detail & Related papers  (2024-05-06T14:11:36Z)
• Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compression [58.618625678054826]
  This study presents an enhanced neural compression method designed for optimal visual fidelity. We have trained our model with a sophisticated semantic ensemble loss, integrating Charbonnier loss, perceptual loss, style loss, and a non-binary adversarial loss. Our empirical findings demonstrate that this approach significantly improves the statistical fidelity of neural image compression.
  arXiv  Detail & Related papers  (2024-01-25T08:11:27Z)
• End-to-End Optimized Image Compression with the Frequency-Oriented Transform [8.27145506280741]
  We propose the end-to-end optimized image compression model facilitated by the frequency-oriented transform. The model enables scalable coding through the selective transmission of arbitrary frequency components. Our model outperforms all traditional codecs including next-generation standard H.266/VVC on MS-SSIM metric.
  arXiv  Detail & Related papers  (2024-01-16T08:16:10Z)
• 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)
• Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression [151.3826781154146]
  latent variables with priors and hyperpriors is an essential problem in variational image compression. We find inter-correlations and intra-correlations exist when observing latent variables in a vectorized perspective. Our model has better rate-distortion performance and an impressive $3.18times$ compression speed up.
  arXiv  Detail & Related papers  (2022-03-21T11:44:17Z)
• Perceptually Optimizing Deep Image Compression [53.705543593594285]
  Mean squared error (MSE) and $ell_p$ norms have largely dominated the measurement of loss in neural networks. We propose a different proxy approach to optimize image analysis networks against quantitative perceptual models.
  arXiv  Detail & Related papers  (2020-07-03T14:33:28Z)
• Improving Inference for Neural Image Compression [31.999462074510305]
  State-of-the-art methods build on hierarchical variational autoencoders to predict a compressible latent representation of each data point. We identify three approximation gaps which limit performance in the conventional approach. We propose remedies for each of these three limitations based on ideas related to iterative inference.
  arXiv  Detail & Related papers  (2020-06-07T19:26:37Z)
• Saliency Driven Perceptual Image Compression [6.201592931432016]
  The paper demonstrates that the popularly used evaluations metrics such as MS-SSIM and PSNR are inadequate for judging the performance of image compression techniques. A new metric is proposed, which is learned on perceptual similarity data specific to image compression. The model not only generates images which are visually better but also gives superior performance for subsequent computer vision tasks.
  arXiv  Detail & Related papers  (2020-02-12T13:43:17Z)

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.