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.
Lossy compression with gaussian diffusion
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
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 reduction over DCVC-RT.
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 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 delivers real-time generative image compression via a lightweight convolution-based diffusion codec with compression-oriented pre-training and distillation, achieving substantial bitrate savings.
RDVQ enables joint rate-distortion optimization for vector-quantized generative image compression via differentiable codebook distribution relaxation and an autoregressive entropy model.
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.
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++ enables high-quality guided sampling of diffusion models in 15-20 steps via data-prediction ODE solving and multistep stabilization.
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.
citing papers explorer
-
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 reduction over DCVC-RT.
-
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.
-
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.