ICE: Intrinsic Concept Extraction from a Single Image via Diffusion Models

Fernando Julio Cendra; Kai Han

doi:10.1109/cvpr52734.2025.02210

CVPR2025顶会

ICE: Intrinsic Concept Extraction from a Single Image via Diffusion Models

Fernando Julio Cendra, Kai Han

DOI 出版方

2025年份

1顶会引用

摘要

Figure 1 . We showcase a structured approach for defining visual concepts within an image, where object-level concepts are identified and analyzed to reveal their underlying intrinsic attributes, such as color, material, and shape. We present the ICE (Intrinsic Concept Extraction) framework, which leverages Text-to-Image (T2I) models to systematically discover these concepts, providing a more effective method for learning visual concepts.