paper-with-me

Papers

One-Step Diffusion-Based Image Compression with Semantic Distillation

2025-05-22 · Naifu Xue, Zhaoyang Jia, Jiahao Li, Bin Li, Yuan Zhang, Yan Lu

While recent diffusion-based generative image codecs have shown impressive performance, their iterative sampling process introduces unpleasing latency. In this work, we revisit the design of a diffusion-based codec and argue that multi-step sampling is not necessary for generative compression. Based on this insight, we propose OneDC, a One-step Diffusion-based generative image Codec -- that integrates a latent compression module with a one-step diffusion generator. Recognizing the critical role of semantic guidance in one-step diffusion, we propose using the hyperprior as a semantic signal, overcoming the limitations of text prompts in representing complex visual content. To further enhance the semantic capability of the hyperprior, we introduce a semantic distillation mechanism that transfers knowledge from a pretrained generative tokenizer to the hyperprior codec. Additionally, we adopt a hybrid pixel- and latent-domain optimization to jointly enhance both reconstruction fidelity and perceptual realism. Extensive experiments demonstrate that OneDC achieves SOTA perceptual quality even with one-step generation, offering over 40% bitrate reduction and 20x faster decoding compared to prior multi-step diffusion-based codecs. Code will be released later.

📄 PDF Abstract BibTeX arXiv:2505.16687

Code (0)

등록된 구현이 없습니다.

Tasks

Image Compression

Methods 이 논문이 사용한 방법론

ADOPT Please enter a description about the method here
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression

2026-03-13 · Junqi Shi, Ming Lu, Xingchen Li, Anle Ke 외 arxiv

Diffusion-based image compression has recently shown outstanding perceptual fidelity, yet its practicality is hindered by prohibitive sampling overhead and high memory usage. Most existing diffusion codecs employ U-Net a…

Image Compression

DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching

2026-02-05 · Chang Zou, Changlin Li, Yang Li, Patrol Li 외 arxiv

While diffusion models have achieved great success in the field of video generation, this progress is accompanied by a rapidly escalating computational burden. Among the existing acceleration methods, Feature Caching is …

Video GenerationImage Generation

CoD-Lite: Real-Time Diffusion-Based Generative Image Compression

2026-04-14 · Zhaoyang Jia, Naifu Xue, Zihan Zheng, Jiahao Li 외 arxiv

Recent advanced diffusion methods typically derive strong generative priors by scaling diffusion transformers. However, scaling fails to generalize when adapted for real-time compression scenarios that demand lightweight…

Image Compression

Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair

2026-07-07 · Jincheng Ying, Li Wenlin, Minghui Xu, Yinhao Xiao arxiv

Diffusion models generate high-quality images, but their inference cost comes from two sources: large denoising networks and repeated denoising steps. Existing compression pipelines usually attack these costs separately.…

Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation

2023-07-17 · ICCV 2023 1 · Luozhou Wang, Shuai Yang, Shu Liu, Ying-Cong Chen

Conditional diffusion models have demonstrated impressive performance in image manipulation tasks. The general pipeline involves adding noise to the image and then denoising it. However, this method faces a trade-off pro…

AllDenoisingImage Manipulation