Article

A Lightweight Perceptual-Guided VQVAE for High-Fidelity Image Compression

2026-03-18

Abstract excerpt

<title>Abstract</title> <p>This study addresses the quality-efficiency trade-off in generative models for low-bit-rate image compression by proposing HiRes-VQ, a lightweight perceptual-guided VQ-VAE framework. The framework inherits the efficient hierarchical quantization architecture of VQ-VAE-2 and innovatively introduces a super-resolution codec. By employing parallel pathways for low-frequency structure recon...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: e80439b2-84a9-5520-8837-b9be88635189
DOI: 10.21203/rs.3.rs-9046607/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

A Lightweight Perceptual-Guided VQVAE for High-Fidelity Image CompressionDOI 10.21203/rs.3.rs-9046607/v1Read

Task-Adaptive Decoder Specialization for Unified Image Coding Toward Human Reconstruction and Machine ClassificationSemantic proximity Read

An Integrated Framework of Frequency-Domain Denoising with Learnable Parameters in Variational AutoencodersSemantic proximity Read

The re-identification generative adversarial network for image super-resolutionSemantic proximity Read

Zero-Shot Image Super-Resolution Using Prompt-Driven Vision-Language Foundation Models Without Task-Specific Fine-TuningSemantic proximity Read

A Systematic Review of Wavelet-Based Pooling for Enhancing GANs: Central Trends, Auxiliary Pooling Strategies, and Complementary Wavelet IntegrationsSemantic proximity Read

MedSAM-prior-guided coarse-to-fine CBCT synthesis from ZTE MRISemantic proximity Read

Neural Steered Mixture of Experts for Medical Image Denoising, and Super-ResolutionSemantic proximity Read

DDASR: Domain-Distance Adapted Super-Resolution Reconstruction of MR Brain ImagesSemantic proximity Read

The Fractional Spectrum: A Unified Adaptive Framework for Image Enhancement via Generalized Derivatives and Multi-Directional FusionSemantic proximity Read

VMDiff: A novel hybrid CNN-Mamba generative framework for retinal phenotype image enhancement.Semantic proximity Read

A Latent Space Diffusion Transformer for High-Quality Video Frame InterpolationSemantic proximity Read

Fundus Image Super-Resolution Based on SRGAN with Efficient Channel Attention and Composite Degradation ModelinSemantic proximity Read