REVIEW 14 cited by
Lossy Compression with Gaussian Diffusion
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Lossy Compression with Gaussian Diffusion
read the original abstract
We consider a novel lossy compression approach based on unconditional diffusion generative models, which we call DiffC. Unlike modern compression schemes which rely on transform coding and quantization to restrict the transmitted information, DiffC relies on the efficient communication of pixels corrupted by Gaussian noise. We implement a proof of concept and find that it works surprisingly well despite the lack of an encoder transform, outperforming the state-of-the-art generative compression method HiFiC on ImageNet 64x64. DiffC only uses a single model to encode and denoise corrupted pixels at arbitrary bitrates. The approach further provides support for progressive coding, that is, decoding from partial bit streams. We perform a rate-distortion analysis to gain a deeper understanding of its performance, providing analytical results for multivariate Gaussian data as well as theoretic bounds for general distributions. Furthermore, we prove that a flow-based reconstruction achieves a 3 dB gain over ancestral sampling at high bitrates.
Forward citations
Cited by 14 Pith papers
-
Covariance-aware sampling for Diffusion Models
A covariance-aware extension of DDIM sampling for pixel-space diffusion models that uses Tweedie's formula and Fourier decomposition to model reverse-process covariance and improves sample quality at low NFE.
-
GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow
GVCC achieves the lowest LPIPS on UVG at bitrates down to 0.003 bpp by encoding stochastic innovations in a marginal-preserving stochastic process derived from a pretrained rectified-flow video model, with 65% LPIPS r...
-
Learning-to-Defer with Expert-Conditional Advice
The paper defines Learning-to-Defer with advice, proves inconsistency of separated surrogate losses, and introduces an augmented surrogate with H-consistency and excess-risk bounds that recovers the Bayes-optimal policy.
-
Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priors
Ultra-low-bitrate image decoding is cast as one-step next-frame prediction from a compact anchor using adapted video diffusion priors, yielding large perceptual bitrate savings versus DiffC.
-
Scalable Differentially Private Data Compression via Diffusion and Stochastic Codes
Step-limited PPR plus Laplace DiffC yields a pure-LDP image compressor that cuts bitrate 10–30× versus privatize-then-compress on CIFAR-10 classification.
-
ZeroGVC: Zero-Shot Generative Video Compression with Autoregressive Diffusion Priors
ZeroGVC performs zero-shot generative video compression by guiding pretrained autoregressive diffusion priors with codebook noise vectors for P-frames after encoding the initial I-frame.
-
Few-step Generative Models as Lossy Compression
Few-step generative models can be reformulated as lossy codecs in the reverse channel coding framework without retraining, yielding faster encoding/decoding on low-resolution image benchmarks.
-
CoD-Lite: Real-Time Diffusion-Based Generative Image Compression
CoD-Lite delivers real-time generative image compression via a lightweight convolution-based diffusion codec with compression-oriented pre-training and distillation, achieving substantial bitrate savings.
-
Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression
RDVQ enables joint rate-distortion optimization for vector-quantized generative image compression via differentiable codebook distribution relaxation and an autoregressive entropy model.
-
A Noise Constrained Diffusion (NC-Diffusion) Framework for High Fidelity Image Compression
NC-Diffusion matches quantization noise to the diffusion forward process, adds an adaptive frequency filter and zero-shot enhancement, and reports superior fidelity on benchmarks.
-
Learning-to-Defer with Expert-Conditional Advice
Separated routing-and-advice surrogates for Learning-to-Defer are inconsistent; a composite expert–advice surrogate is H-consistent and recovers the Bayes-optimal policy in the limit.
-
Training-Free Rate-Distortion-Perception Traversal With Diffusion
A training-free diffusion-based method with RCC module and score-scaled PF-ODE decoder achieves optimal RDP in the Gaussian case and allows empirical traversal of the ternary tradeoff surface.
-
DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
DPM-Solver++ enables high-quality guided sampling of diffusion models in 15-20 steps via data-prediction ODE solving and multistep stabilization.
-
On the Robustness of Diffusion-Based Image Compression to Bit-Flip Errors
Diffusion-based compressors using reverse channel coding are substantially more robust to bit-flip errors than classical and learned codecs, and a new variant of Turbo-DDCM improves this further.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.