Q-Refine: A Perceptual Quality Refiner for AI-Generated Image (2401.01117v1)
Abstract: With the rapid evolution of the Text-to-Image (T2I) model in recent years, their unsatisfactory generation result has become a challenge. However, uniformly refining AI-Generated Images (AIGIs) of different qualities not only limited optimization capabilities for low-quality AIGIs but also brought negative optimization to high-quality AIGIs. To address this issue, a quality-award refiner named Q-Refine is proposed. Based on the preference of the Human Visual System (HVS), Q-Refine uses the Image Quality Assessment (IQA) metric to guide the refining process for the first time, and modify images of different qualities through three adaptive pipelines. Experimental shows that for mainstream T2I models, Q-Refine can perform effective optimization to AIGIs of different qualities. It can be a general refiner to optimize AIGIs from both fidelity and aesthetic quality levels, thus expanding the application of the T2I generation models.
- “Agiqa-3k: An open database for ai-generated image quality assessment,” IEEE TCSVT, 2023.
- “Adversarial text-to-image synthesis: A review,” Neural Networks, 2021.
- “Text-to-image diffusion model in generative ai: A survey,” arXiv:2303.07909, 2023.
- “Unsupervised real-world image super resolution via domain-distance aware training,” in IEEE/CVF CVPR, 2021.
- “Diffbir: Towards blind image restoration with generative diffusion prior,” arXiv:2308.15070, 2023.
- “Residual feature distillation network for lightweight image super-resolution,” in ECCV, 2020.
- “High-resolution image synthesis with latent diffusion models,” in IEEE CVPR, 2022.
- “Text-guided synthesis of artistic images with retrieval-augmented diffusion models,” arXiv:2207.13038, 2022.
- “Stablevqa: A deep no-reference quality assessment model for video stability,” in ACM MM, 2023.
- “Vdpve: Vqa dataset for perceptual video enhancement,” in IEEE/CVF CVPR, 2023.
- “A real-time blind quality-of-experience assessment metric for http adaptive streaming,” in IEEE ICME, 2023.
- “A full-reference quality assessment metric for cartoon images,” in IEEE MMSP, 2022.
- “Xgc-vqa: A unified video quality assessment model for user, professionally, and occupationally-generated content,” in IEEE ICMEW, 2023.
- “Q-bench: A benchmark for general-purpose foundation models on low-level vision,” arXiv:2309.14181, 2023.
- “Q-instruct: Improving low-level visual abilities for multi-modality foundation models,” arXiv:2311.06783, 2023.
- “Q-boost: On visual quality assessment ability of low-level multi-modality foundation models,” arXiv:2312.15300, 2023.
- “Advancing zero-shot digital human quality assessment through text-prompted evaluation,” arXiv:2307.02808, 2023.
- “Gms-3dqa: Projection-based grid mini-patch sampling for 3d model quality assessment,” arXiv:2306.05658, 2023.
- “From patches to pictures (paq-2-piq): Mapping the perceptual space of picture quality,” in IEEE/CVF CVPR, 2020.
- “Faster r-cnn: Towards real-time object detection with region proposal networks,” NIPS, 2015.
- “Pixart-α𝛼\alphaitalic_α: Fast training of diffusion transformer for photorealistic text-to-image synthesis,” arXiv:2310.00426, 2023.
- Dianyuan Han, “Comparison of commonly used image interpolation methods,” in ICCSEE, 2013.
- “Best prompts for text-to-image models and how to find them,” in ACM SIGIRl, 2023.
- “Glide: Towards photorealistic image generation and editing with text-guided diffusion models,” in ICML, 2022.
- “Hierarchical text-conditional image generation with clip latents,” arXiv:2204.06125, 2022.
- David Holz, “Midjourney,” https://www.midjourney.com/, 2023.
- “A perceptual quality assessment exploration for aigc images,” in IEEE ICMEW, 2023.
- “Aigciqa2023: A large-scale image quality assessment database for ai generated images: from the perspectives of quality, authenticity and correspondence,” in CICAI, 2023.
- “Gans trained by a two time-scale update rule converge to a local nash equilibrium,” in NIPS, 2017.
- “No-reference image quality assessment in the spatial domain,” IEEE TIP, 2012.
- “Blindly assess image quality in the wild guided by a self-adaptive hyper network,” in IEEE/CVF CVPR, 2020.
- “Exploring clip for assessing the look and feel of images,” in AAAI, 2023.
Sponsored by Paperpile, the PDF & BibTeX manager trusted by top AI labs.
Get 30 days freePaper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.