Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
H-DDCM replaces dense Gaussian codebooks in training-free diffusion compression with implicit randomized Hadamard dictionaries, enabling $O(d \log d)$ projection and reconstruction compute and $O(d)$ memory. This framework, coupled with a practical lexicographic coding scheme, achieves competitive rate-distortion-perception performance for images and enables near real-time generative video compression via a novel streaming approach. The method substantially reduces the computational and memory overhead of prior codebook-based generative compression techniques.
Generative image and video compression achieves significant memory and compute reduction by replacing dense Gaussian codebooks with implicit randomized Hadamard dictionaries, enabling real-time streaming video compression on a single GPU.
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.