mlsanityData to 7 Oct 2026

Towards Defining an Efficient and Expandable File Format for AI-Generated Contents

arXiv 2410.09834 ↗First posted 13 Oct 2024cs.CV eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recently, AI-generated content (AIGC) has gained significant traction due to its powerful creation capability. However, the storage and transmission of large amounts of high-quality AIGC images inevitably pose new challenges for recent file formats. To overcome this, we define a new file format for AIGC images, named AIGIF, enabling ultra-low bitrate coding of AIGC images. Unlike compressing AIGC images intuitively with pixel-wise space as existing file formats, AIGIF instead compresses the generation syntax. This raises a crucial question: Which generation syntax elements, e.g., text prompt, device configuration, etc, are necessary for compression/transmission? To answer this question, we systematically investigate the effects of three essential factors: platform, generative model, and data configuration. We experimentally find that a well-designed composable bitstream structure incorporating the above three factors can achieve an impressive compression ratio of even up to 1/10,000 while still ensuring high fidelity. We also introduce an expandable syntax in AIGIF to support the extension of the most advanced generation models to be developed in the future.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 36 references that are in the map. First posted on arXiv 13 Oct 2024.

Builds on

27 of 36 references.

References · 27

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  8. 2022Scalable Diffusion Models with Transformerscited by 5,931
  9. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  10. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  11. 2023Consistency Modelscited by 1,778
  12. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
15 more
  1. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 826
  2. 2022On Distillation of Guided Diffusion Modelscited by 721
  3. 2023Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystackcited by 278
  4. 2022Post-training Quantization on Diffusion Modelscited by 262
  5. 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Secondscited by 227
  6. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 165
  7. 2023DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statisticscited by 161
  8. 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesiscited by 153
  9. 2023Towards image compression with perfect realism at ultra-low bitratescited by 99
  10. 2024LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insightscited by 65
  11. 2023High-Fidelity Image Compression with Score-based Generative Modelscited by 53
  12. 2023Knowledge Diffusion for Distillationcited by 51
  13. 2023A Residual Diffusion Model for High Perceptual Quality Codec Augmentationcited by 33
  14. 2024Idempotence and Perceptual Image Compressioncited by 27
  15. 2023ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generationscited by 24

Built on by

Not cited yet.