GEODIFFUSION: TEXT-PROMPTED GEOMETRIC CONTROL FOR OBJECT DETECTION DATA GENERATION

doi:doi:10.57702/kvneiw7f

GEODIFFUSION: TEXT-PROMPTED GEOMETRIC CONTROL FOR OBJECT DETECTION DATA GENERATION

Diffusion models have attracted significant attention due to the remarkable ability to create content and generate data for tasks like image classification. However, the usage of diffusion models to generate the high-quality object detection data remains an underexplored area, where not only image-level perceptual quality but also geometric conditions such as bounding boxes and camera views are essential.

BibTex:

@dataset{Kai_Chen_and_Enze_Xie_and_Zhe_Chen_and_Yibo_Wang_and_Lanqing_Hong_and_Zhenguo_Li_and_Dit-Yan_Yeung_2024,
    abstract = {Diffusion models have attracted significant attention due to the remarkable ability to create content and generate data for tasks like image classification. However, the usage of diffusion models to generate the high-quality object detection data remains an underexplored area, where not only image-level perceptual quality but also geometric conditions such as bounding boxes and camera views are essential.},
    author = {Kai Chen and Enze Xie and Zhe Chen and Yibo Wang and Lanqing Hong and Zhenguo Li and Dit-Yan Yeung},
    doi = {10.57702/kvneiw7f},
    institution = {No Organization},
    keyword = {'diffusion models', 'geometric control', 'image generation', 'object detection'},
    month = {dec},
    publisher = {TIB},
    title = {GEODIFFUSION: TEXT-PROMPTED GEOMETRIC CONTROL FOR OBJECT DETECTION DATA GENERATION},
    url = {https://service.tib.eu/ldmservice/dataset/geodiffusion--text-prompted-geometric-control-for-object-detection-data-generation},
    year = {2024}
}