Update on Diffusion model-based Image/Video Compression

[tongdaxu]

Hi,

Thanks for this cool work. Would you mind appending our work on diffusion image codec?

idempotence and perceptual image compression, ICLR 2024 Arxiv: https://arxiv.org/abs/2401.08920 Code: https://github.com/tongdaxu/idempotence-and-perceptual-image-compression

Besides, TOWARDS IMAGE COMPRESSION WITH PERFECT REALISM AT ULTRA-LOW BITRATES is also accepted by ICLR 2024.

A typo, Lossy Image Compression with Conditional Diffusion Models is presented in ICML 2023 workshop and accepted in NeurIPS 2024, not ICLR 2023. Text + Sketch: Image Compression at Ultra Low Rates is also presented in ICML 2023 workshop.

@lixinustc

[lixinustc]

Thanks for your very excellent works, we will incorporate these works into our repo, and revise the corresponding parts.

[tongdaxu]

Thanks for your very excellent works, we will incorporate these works into our repo, and revise the corresponding parts.

Thanks for including this, some bug fixs:

• Lossy Image Compression with Conditional Diffusion Models is published in NeurIPS 2023, not NeurIPS 2024 (I made a mistake, sorry!). The code is also released in https://github.com/buggyyang/cdc_compression
• Idempotence and Perceptual Image Compression is already published in ICLR 2024.

Thanks for your time

@lixinustc

[lixinustc]

Thanks for your reminding. I will incorporate it into this repo.