CVDec 10, 2024

FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models

arXiv:2412.07674v13 citationsh-index: 16NIPS
Originality Incremental advance
AI Analysis

This work addresses user-friendly customization for non-experts in art and photography by enabling fine-grained control over visual attributes in generated images, though it is incremental in improving existing adaptation methods.

The paper tackles the challenge of accurately describing visual attributes in text-to-image generation by decomposing aesthetics into specific attributes like lighting and dynamics, resulting in a dataset of 1M annotated images and a framework that enables selective attribute adaptation from multiple sources.

Recent advances in text-to-image generation have enabled the creation of high-quality images with diverse applications. However, accurately describing desired visual attributes can be challenging, especially for non-experts in art and photography. An intuitive solution involves adopting favorable attributes from the source images. Current methods attempt to distill identity and style from source images. However, "style" is a broad concept that includes texture, color, and artistic elements, but does not cover other important attributes such as lighting and dynamics. Additionally, a simplified "style" adaptation prevents combining multiple attributes from different sources into one generated image. In this work, we formulate a more effective approach to decompose the aesthetics of a picture into specific visual attributes, allowing users to apply characteristics such as lighting, texture, and dynamics from different images. To achieve this goal, we constructed the first fine-grained visual attributes dataset (FiVA) to the best of our knowledge. This FiVA dataset features a well-organized taxonomy for visual attributes and includes around 1 M high-quality generated images with visual attribute annotations. Leveraging this dataset, we propose a fine-grained visual attribute adaptation framework (FiVA-Adapter), which decouples and adapts visual attributes from one or more source images into a generated one. This approach enhances user-friendly customization, allowing users to selectively apply desired attributes to create images that meet their unique preferences and specific content requirements.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes