跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-13AI 評分35

H-DDCM: Hadamard Codebooks for Fast Generative Image and Video Compression

H-DDCM: Hadamard Codebooks for Fast Generative Image and Video Compression

AI 導讀

H-DDCM 以隱式隨機 Hadamard 字典及免查表字典序編碼,取代稠密 Gaussian 碼本,降低免訓練生成式圖像與影片壓縮的記憶體及計算開銷。快速 Walsh-Hadamard 轉換以 O(d log d) 計算量完成投影與重建,記憶體用量為 O(d)。該方法亦支援自回歸影片 flow 模型,可在單張 GPU 上進行長片段、接近即時的生成式影片壓縮。

正文

Published on Oct 13

Authors:

,

Abstract

H-DDCM replaces dense Gaussian codebooks with implicit randomized Hadamard dictionaries and table-free lexicographic coding to enable scalable, efficient generative image and video compression using diffusion and flow models.

Training-free diffusion-based compression methods repurpose the generative priors of a diffusion or a flow model to compress data without retraining them as task-specific codecs. Recent codebook-based approaches such as Turbo-DDCM achieve strong perceptual quality at ultra-low bitrates, but their reliance on dense Gaussian codebooks remains costly in both memory and computation, and scales poorly with the large latent dimensions of modern image and video generators. Their combinatorial bitstream encoding further becomes computationally heavy at this scale. We introduce H-DDCM, a scalable generative compression framework that replaces Gaussian codebooks with implicit randomized Hadamard dictionaries. The fast Walsh-Hadamard transform allows for implicitly synthesizing full-dimensional dictionaries with O(d log d) compute for projection and reconstruction and O(d) memory, without materializing the full-dimensional dictionary. We further introduce an efficient table-free lexicographic coding scheme that makes combinatorial encoding practical at larger dimensions. Beyond images, we adapt the framework to an autoregressive video flow model and develop a streaming compression scheme that periodically re-encodes recently reconstructed frames into a fresh KV-cache prefix, preserving temporal context across segments at no additional transmitted bits. This enables long-form, close to real-time generative video compression on a single GPU. Across image and video benchmarks, H-DDCM achieves competitive rate-distortion-perception performance while substantially reducing the memory and computational overhead of codebook-based training-free generative compression.

View arXiv page View PDF Project page Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.18125 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.18125 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.18125 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co