Training-Free Rate-Distortion-Perception Traversal With Diffusion

• URL: http://arxiv.org/abs/2603.04005v1
• Date: Wed, 04 Mar 2026 12:49:13 GMT
• Title: Training-Free Rate-Distortion-Perception Traversal With Diffusion
• Authors: Yuhan Wang, Suzhi Bi, Ying-Jun Angela Zhang,
• Abstract summary: We propose a training-free framework that leverages pre-trained diffusion models to traverse the entire surface.<n>Our results establish a practical and theoretically grounded approach to neural-aware compression.
• Score: 44.11458502528137
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rate-distortion-perception (RDP) tradeoff characterizes the fundamental limits of lossy compression by jointly considering bitrate, reconstruction fidelity, and perceptual quality. While recent neural compression methods have improved perceptual performance, they typically operate at fixed points on the RDP surface, requiring retraining to target different tradeoffs. In this work, we propose a training-free framework that leverages pre-trained diffusion models to traverse the entire RDP surface. Our approach integrates a reverse channel coding (RCC) module with a novel score-scaled probability flow ODE decoder. We theoretically prove that the proposed diffusion decoder is optimal for the distortion-perception tradeoff under AWGN observations and that the overall framework with the RCC module achieves the optimal RDP function in the Gaussian case. Empirical results across multiple datasets demonstrate the framework's flexibility and effectiveness in navigating the ternary RDP tradeoff using pre-trained diffusion models. Our results establish a practical and theoretically grounded approach to adaptive, perception-aware compression.

Related papers

• Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols [123.73663884421272]
  Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.<n>We establish FEWTRANS, a comprehensive benchmark containing 10 diverse datasets.<n>By releasing FEWTRANS, we aim to provide a rigorous "ruler" to streamline reproducible advances in few-shot transfer learning research.
  arXiv  Detail & Related papers  (2026-02-28T05:41:57Z)
• SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation [62.14510717860079]
  We propose a Synergistic Diffusion-Autoregression paradigm that unifies the training efficiency of autoregressive models with the parallel inference capability of diffusion.<n>SDAR performs a lightweight paradigm conversion that transforms a well-trained autoregressive (AR) model into a blockwise diffusion model through brief, data-efficient adaptation.<n>Building on this insight, SDAR achieves efficient AR-to-diffusion conversion with minimal cost, preserving AR-level performance while enabling parallel generation.
  arXiv  Detail & Related papers  (2025-10-07T17:29:28Z)
• Traversing Distortion-Perception Tradeoff using a Single Score-Based Generative Model [35.91741991271154]
  distortion-perception tradeoff reveals a fundamental conflict between distortion metrics and perceptual quality.<n>We show that a single score network can effectively and flexibly traverse the DP tradeoff for general denoising problems.
  arXiv  Detail & Related papers  (2025-03-26T07:37:53Z)
• Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoff [29.69773024077467]
  Recent efforts in neural compression have focused on the rate-distortion-perception tradeoff, where the perception constraint ensures the source and reconstruction are close in terms of a statistical divergence.<n>While classical rate distortion theory shows that optimal compressors should efficiently pack space, theory additionally shows that infinite randomness shared between the encoder and decoder may be necessary for optimality.
  arXiv  Detail & Related papers  (2025-03-21T22:18:52Z)
• SING: Semantic Image Communications using Null-Space and INN-Guided Diffusion Models [52.40011613324083]
  Joint source-channel coding systems (DeepJSCC) have recently demonstrated remarkable performance in wireless image transmission.<n>Existing methods focus on minimizing distortion between the transmitted image and the reconstructed version at the receiver, often overlooking perceptual quality.<n>We propose SING, a novel framework that formulates the recovery of high-quality images from corrupted reconstructions as an inverse problem.
  arXiv  Detail & Related papers  (2025-03-16T12:32:11Z)
• Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual [47.141811103506036]
  We propose a novel zero-shot image restoration scheme dubbed Reconciling Model in Dual (RDMD)<n>RDMD uses only a bftextsingle pre-trained diffusion model to construct texttwo regularizers.<n>Our proposed method could achieve superior results compared to existing approaches on both the FFHQ and ImageNet datasets.
  arXiv  Detail & Related papers  (2025-03-03T08:25:22Z)
• Half-order Fine-Tuning for Diffusion Model: A Recursive Likelihood Ratio Optimizer [16.103949557802988]
  probabilistic diffusion model (DM) generates content by inferencing through a chain structure.<n>Modern methods are either based on Reinforcement Learning (RL) or truncated Backpropagation (BP)<n>We propose the Recursive Likelihood Ratio (RLR) fine-tuning paradigm for DM.
  arXiv  Detail & Related papers  (2025-02-02T03:00:26Z)
• Rectified Diffusion Guidance for Conditional Generation [94.83538269086613]
  We revisit the theory behind CFG and rigorously confirm that the improper combination coefficients (textiti.e.) brings about expectation shift the generative distribution.<n>We show that our approach enjoys a textbftextitform solution given the strength.<n> Empirical evidence on real-world data demonstrate the compatibility of our design with existing state-of-the-art diffusion models.
  arXiv  Detail & Related papers  (2024-10-24T13:41:32Z)
• Test-time adaptation for image compression with distribution regularization [43.490138269939344]
  We introduce a simple Bayesian approximation-endowed textit distribution regularization to encourage learning a better joint probability approximation in a plug-and-play manner. Our proposed method not only improves the R-D performance compared with other latent refinement counterparts, but also can be flexibly integrated into existing TTA-IC methods with incremental benefits.
  arXiv  Detail & Related papers  (2024-10-16T03:25:16Z)
• Reflected Diffusion Models [93.26107023470979]
  We present Reflected Diffusion Models, which reverse a reflected differential equation evolving on the support of the data. Our approach learns the score function through a generalized score matching loss and extends key components of standard diffusion models.
  arXiv  Detail & Related papers  (2023-04-10T17:54:38Z)

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.