REVIEW 14 cited by
High-Fidelity Image Compression with Score-based Generative Models
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
Signed reviews
read the original abstract
Despite the tremendous success of diffusion generative models in text-to-image generation, replicating this success in the domain of image compression has proven difficult. In this paper, we demonstrate that diffusion can significantly improve perceptual quality at a given bit-rate, outperforming state-of-the-art approaches PO-ELIC and HiFiC as measured by FID score. This is achieved using a simple but theoretically motivated two-stage approach combining an autoencoder targeting MSE followed by a further score-based decoder. However, as we will show, implementation details matter and the optimal design decisions can differ greatly from typical text-to-image models.
Forward citations
Cited by 14 Pith papers
-
Progressive Compression with Universally Quantized Diffusion Models
A uniform-noise diffusion model plus universal quantization enables a single-model progressive image codec that is computationally tractable and competitive with classic and neural baselines.
-
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.
-
SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization
A GAN-free, single-step distilled diffusion decoder that reconstructs images from latent codes with better perceptual FID than KL-VAE at higher throughput.
-
StableCodec: Taming One-Step Diffusion for Extreme Image Compression
A one-step diffusion codec that compresses noisy latents at 64x and decodes with a single denoising step, setting state-of-the-art FID, KID, and DISTS at ultra-low bitrates.
-
Generative Image Compression by Estimating Gradients of the Rate-variable Feature Distribution
A single rate-variable generative compression model treats quantization as a forward corruption and reverses it with a two-step denoiser, outperforming prior generative codecs on perceptual quality benchmarks.
-
Higher fidelity perceptual image and video compression with a latent conditioned residual denoising diffusion model
ResCDC combines a fidelity-optimized decoder with a latent-conditioned residual denoising diffusion model to improve PSNR by up to 2 dB over CDC while retaining similar LPIPS and FID.
-
Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion
ResULIC combines residual text captions, optimized prompts, and bitrate-aware diffusion steps to reach state-of-the-art perceptual quality at ultra-low bitrates.
-
Why Compress What You Can Generate? When GPT-4o Generation Ushers in Image Compression Fields
A structured raster-scan prompt fed to GPT-4o can reconstruct images at ultra-low bitrates (around 0.001 bpp) with competitive perceptual quality versus trained generative codecs, though only demonstrated on 10 images.
-
UniMIC: Towards Universal Multi-modality Perceptual Image Compression
A single text-conditioned diffusion refiner improves perceptual quality (FID, LPIPS) of images from eight different base codecs and extends to unseen codecs.
-
Is JPEG AI going to change image forensics?
JPEG AI compression adds upsampling-like artifacts that push pristine images into the deepfake class and blind splicing localization, an effect that is opposite to standard JPEG and stronger at low bitrates.
-
Fast Training-free Perceptual Image Compression
A noise-then-denoise decoder with a pre-trained diffusion model turns any existing codec into a fast, training-free perceptual codec with a KL-divergence guarantee and 0.1-10s decoding.
-
Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression
Transform coding in a VQ-VAE latent space, instead of pixel space, yields 45% bitrate savings over MS-ILLM at equal FID for images and 65.3% DISTS-based bitrate savings over PLVC for video at ultra-low bitrates.
-
Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression
A pretrained neural image codec can be augmented with a decoder-side latent diffusion module and a τ slider that interpolates between low-distortion and high-perception reconstructions without changing the bitstream.
-
Synonymous Variational Inference for Perceptual Image Compression
A synonym-set formulation of variational inference re-derives the rate-distortion-perception tradeoff and is demonstrated with a single progressive image codec.
Discussion (0). Continue with ORCID to comment.