rate-distortion analysis

This study addresses the problem of compressing random variables under three simultaneous constraints: distortion (fidelity), perceptual naturalness, and a newly introduced deception constraint that requires reconstructed samples to appear as if drawn from a target distribution. By incorporating this deception constraint into the classical rate–distortion framework, the work extends traditional information-theoretic analysis to cross-distribution camouflage scenarios. Leveraging an information-theoretic formulation combined with distributional distance measures, the authors derive fundamental limits of compression under deception and establish a precise trade-off among rate, distortion, and deception. This theoretical advance provides a new foundation for applications such as privacy-preserving data release and adversarial data obfuscation.

This study addresses the challenge of balancing compression efficiency and perceptual audio quality in audio codec selection. Methodologically, it introduces a human auditory perception–centered evaluation framework integrating the Perceptual Evaluation of Audio Quality (PEAQ) objective model, multi-bitrate encoding performance testing, time-frequency spectrogram visualization, and multidimensional quality analysis to quantitatively characterize distortion mechanisms affecting perceived sound quality. Its key contribution lies in the first systematic, cross-codec comparison—under standardized experimental conditions—of mainstream codecs (e.g., MP3, AAC, Opus, FLAC) along their rate–perceptual-quality trade-off curves, revealing distinct patterns of perceptual degradation. The results provide reproducible empirical evidence and application-oriented, quality-efficiency co-optimization guidelines for codec selection across diverse use cases.

Current CVQE research suffers from three key limitations: (1) the absence of a systematic taxonomy linking video coding standards to compression artifacts; (2) a lack of cross-standard architectural comparisons (e.g., H.264/AVC, H.265/HEVC, H.266/VVC); and (3) fragmented, non-reproducible benchmarking practices. To address these, we propose the first classification framework explicitly modeling the coupling between compression-domain features and coding standards. We establish a unified, multi-standard (H.264–H.266), multi-sequence, multi-metric evaluation benchmark. Furthermore, we conduct fair, architecture-agnostic, and codec-agnostic performance assessment of state-of-the-art deep learning-based CVQE methods. Experimental analysis uncovers fundamental trade-offs between accuracy and computational complexity, yielding reproducible empirical insights for model selection and algorithm design. All components—including benchmarks, evaluation protocols, and open-source tooling—are publicly released to foster standardized, transparent, and comparable CVQE research.

This study challenges the presumed necessity of hierarchical quantization in Vector Quantized Variational Autoencoders (VQ-VAEs) for achieving high reconstruction quality. By systematically comparing single-layer and two-layer VQ-VAE architectures with matched representational capacity on high-resolution ImageNet, the work evaluates the actual contribution of hierarchical structure to reconstruction fidelity. Lightweight strategies—including data-driven codebook initialization, periodic resetting of inactive codebook vectors, and careful hyperparameter tuning—are employed to mitigate codebook collapse and enhance codebook utilization. Under controlled representational budgets and effective collapse suppression, the results demonstrate that a single-layer VQ-VAE can achieve reconstruction performance comparable to its hierarchical counterpart, thereby questioning the widely held assumption that hierarchical architectures are inherently superior.

Existing vector quantization (VQ) generative models rely on fixed codebooks, resulting in inflexible bitrates, the need for repeated retraining, and a fundamental trade-off between compression efficiency and reconstruction fidelity. This work proposes a multi-rate codebook adaptation framework that, for the first time, enables a single pre-trained VQ model to generate discrete representations at arbitrary bitrates without retraining. Our approach comprises two key innovations: (1) a data-driven mechanism for generating multi-rate codebooks, and (2) a lightweight adaptation method for pre-trained VQ models, leveraging hierarchical clustering and codebook embedding interpolation. Experiments demonstrate consistent and significant improvements over fixed-codebook baselines across diverse bitrates. The framework supports continuous, fine-grained rate-distortion control, substantially enhancing the generalizability, deployment flexibility, and inference efficiency of VQ models in practical applications.

This work addresses the challenge of optimizing rate-distortion trade-offs in video compression below 0.1 bits per pixel (bpp), where existing methods struggle due to the absence of differentiable rate signals. The authors propose MS-VQ-VAE, a framework leveraging discrete latent variables and vector quantization combined with an autoregressive prior to model codebook usage distributions, enabling ultra-low-bitrate compression without explicit rate penalties. By revealing that codebook utilization follows a power-law distribution, they employ entropy coding to push empirical bitrates below theoretical limits. To stabilize training with small codebooks, they introduce exponential moving average (EMA) codebook updates and a dead-code revival mechanism, mitigating gradient collapse. On UCF101, the method achieves 0.043–0.064 bpp—5× to 7.6× more efficient than H.265—and consistently surpasses H.265 (CRF=36) in perceptual quality measured by LPIPS, with gains up to 0.072.

This work addresses the limitations of traditional video compression, which often degrades semantic understanding by downstream vision-language models (VLMs) and fails to reduce inference calls. To overcome these issues, the authors propose BLUE—the first semantics-preserving compression method tailored for machine vision in fixed-camera surveillance scenarios. BLUE leverages foreground-background separation to suppress redundancy from static backgrounds while preserving semantically critical activity content. Built upon the H.265 framework, it integrates content-aware compression with a packet-size-driven frame-skipping strategy. Experiments on the VIRAT and CHAD datasets demonstrate that BLUE reduces VLM inference calls by an estimated 53% without significant loss in semantic quality, thereby achieving decoupled optimization of compression efficiency and semantic fidelity.

This work addresses the challenge of achieving a balance among perceptual quality, semantic consistency, and pixel-level fidelity in image compression at ultra-low bitrates (<0.03 bpp), where existing methods often fall short. To this end, the authors propose SPRDiff, a novel approach that synergistically integrates semantic and pixel-level representations. SPRDiff employs a three-encoder architecture to jointly extract pretrained semantic features and distortion-oriented features, and introduces a distortion-aware reconstruction module that enables dual-level conditional guidance within a diffusion-based compression framework. Notably, the method operates with a frozen VAE encoder and significantly outperforms current state-of-the-art techniques, achieving an optimal trade-off between perceptual quality and pixel fidelity under extremely constrained bitrates.

This work addresses the limitations of existing adaptive bitrate streaming systems, which rely on static bitrate ladders and objective quality metrics ill-suited for live scenarios, leading to inaccurate resolution switching decisions. To overcome this, the authors propose a Dynamic Resolution Switching (DRS) framework that, while remaining compatible with current streaming protocols, dynamically constructs content-adaptive bitrate ladders in real time by leveraging user bandwidth distributions and resolution crossover regions. For the first time, a lightweight stream quality assessment model optimized for subjective switching-point prediction is integrated to guide adaptation decisions. The proposed method achieves approximately 9% BD-rate gain over baseline approaches while maintaining low latency and practicality for live streaming, substantially improving quality-efficiency trade-offs.

Existing learned image compression methods struggle to simultaneously achieve high distortion fidelity and perceptual realism across a wide bitrate range. To address this challenge, this work proposes the Mixture of Decoder Experts (MoDE) framework, which introduces, for the first time, dual latent representations—scalar quantization (SQ) and vector quantization (VQ)—at the decoder side to separately optimize fidelity and perceptual objectives. The framework incorporates Expert-Specific Enhancement (ESE) and Cross-Expert Modulation (CEM) mechanisms to enable complementary collaboration between the two expert decoders. Operating under a unified bitstream, MoDE supports flexible decoding and consistently achieves superior rate–fidelity–perception trade-offs across low to high bitrates, thereby validating the effectiveness of the dual-stream collaborative architecture at the decoder.