# Dual-Constrained Diffusion Image Compression for Operational Rate-Distortion-Perception Optimization

arXiv: https://arxiv.org/abs/2606.13366 · HTML: https://mlsanity.com/paper/2606.13366/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 47 references that are in the map.
- First posted on arXiv 11 Jun 2026.

## Builds on (most cited first, 30 of 30)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2201.11793/) (2022)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [Fast Sampling of Diffusion Models with Exponential Integrator](https://mlsanity.com/paper/2204.13902/) (2022)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff](https://mlsanity.com/paper/1901.07821/) (2019)
- [Learned Image Compression with Mixed Transformer-CNN Architectures](https://mlsanity.com/paper/2303.14978/) (2023)
- [Lossy Image Compression with Conditional Diffusion Models](https://mlsanity.com/paper/2209.06950/) (2022)
- [Generative Modeling via Drifting](https://mlsanity.com/paper/2602.04770/) (2026)
- [Entroformer: A Transformer-based Entropy Model for Learned Image Compression](https://mlsanity.com/paper/2202.05492/) (2022)
- [Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models](https://mlsanity.com/paper/2301.11189/) (2023)
- [Multi-Realism Image Compression with a Conditional Generator](https://mlsanity.com/paper/2212.13824/) (2022)
- [Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2304.03322/) (2023)
- [Learned Block-based Hybrid Image Compression](https://mlsanity.com/paper/2012.09550/) (2020)
- [Idempotence and Perceptual Image Compression](https://mlsanity.com/paper/2401.08920/) (2024)
- [The Rate-Distortion-Perception Tradeoff: The Role of Common Randomness](https://mlsanity.com/paper/2202.04147/) (2022)
- [Rate-Distortion-Cognition Controllable Versatile Neural Image Compression](https://mlsanity.com/paper/2407.11700/) (2024)
- [PICD: Versatile Perceptual Image Compression with Diffusion Rendering](https://mlsanity.com/paper/2505.05853/) (2025)
- [Q-LIC: Quantizing Learned Image Compression with Channel Splitting](https://mlsanity.com/paper/2205.14510/) (2022)
- [Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimization](https://mlsanity.com/paper/2405.14221/) (2024)

## Abstract (arXiv)

The rate-distortion-perception (RDP) trade-off extends classical rate--distortion theory by imposing a distributional constraint on reconstructions, providing a unified framework for neural image compression that jointly governs fidelity and perceptual realism. While prior work achieves near-optimal rate--perception trade-offs, practical frameworks explicitly realizing the full RDP surface remain scarce, primarily due to the difficulty of introducing common randomness at the decoder. We propose DCIC (Dual-Constrained Diffusion Image Compression), which integrates a learned codec with a diffusion-based decoder governed by joint distortion and idempotence constraints. The distortion constraint bounds reconstruction fidelity relative to the base codec output; the idempotence constraint -- requiring that re-encoding the restored image recovers the base codec reconstruction -- serves as a tractable surrogate for the distributional perception requirement. Together, they steer the reverse denoising process via iterative optimization with consistent noise injection, realizing common randomness without additional rate overhead. At fixed rate, dual attenuation factors (KD, KP) jointly navigate the Pareto frontier of the distortion-perception plane, enabling continuously adjustable fidelity-realism trade-offs from a single bitstream. DCICRD (KP=0) and DCICRP (KD=0) arise as boundary curves, with DCICRDP (KD = KP=1) realizing the optimal interior operating point. Experiments on CelebA-HQ, CLIC2020, and ImageNet-1K across CNN, Transformer, and hybrid architectures confirm that DCICRDP achieves superior BD-PSNR over all perceptual codecs, while DCICRP matches dedicated perception-oriented methods in BD-FID, validating the practical value of full RDP surface navigation.