SPRDiff is a diffusion model for ultra-low bitrate image compression that fuses features from distortion-oriented, semantic-oriented, and VAE encoders plus a dual-feature reconstruction module to outperform prior methods on rate-distortion-perception trade-offs.
Stablecodec: Taming one-step diffusion for extreme image compression.arXiv preprint arXiv:2506.21977, 2025a
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 3verdicts
UNVERDICTED 3roles
baseline 1polarities
baseline 1representative citing papers
RDVQ enables joint rate-distortion optimization for vector-quantized generative image compression via differentiable codebook distribution relaxation and an autoregressive entropy model.
Introduces a benchmark for VLMs on compressed images and a universal adaptor to improve performance across codecs and bitrates.
citing papers explorer
-
Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression
SPRDiff is a diffusion model for ultra-low bitrate image compression that fuses features from distortion-oriented, semantic-oriented, and VAE encoders plus a dual-feature reconstruction module to outperform prior methods on rate-distortion-perception trade-offs.
-
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.
-
Benchmarking and Enhancing VLM for Compressed Image Understanding
Introduces a benchmark for VLMs on compressed images and a universal adaptor to improve performance across codecs and bitrates.