9 papers · 1 filter
Editing Everything Everywhere All at Once
Fabio Quattrini, Carmine Zaccagnino, Enis Simsar +4
Editing multiple elements of an image in a single forward pass is a practical alternative to multi-turn image manipulation, offering improved efficiency and potentially better harm…
A Text Recognition Dataset from Sahidic Coptic Ancient Manuscripts
Fabio Quattrini, Carmine Zaccagnino, Costanza Bianchi +2
In this work, we target Handwritten Text Recognition (HTR) in low-resource scenarios, which arise from underrepresented languages, rare scripts, and degraded visual conditions typi…
Shifting the Breaking Point of Flow Matching for Multi-Instance Editing
Carmine Zaccagnino, Fabio Quattrini, Enis Simsar +4
Flow matching models have recently emerged as an efficient alternative to diffusion, especially for text-guided image generation and editing, offering faster inference through cont…
Autoregressive Styled Text Image Generation, but Make it Reliable
Carmine Zaccagnino, Fabio Quattrini, Vittorio Pippi +3
Generating faithful and readable styled text images (especially for Styled Handwritten Text generation - HTG) is an open problem with several possible applications across graphic d…
Zero-Shot Styled Text Image Generation, but Make It Autoregressive
Vittorio Pippi, Fabio Quattrini, Silvia Cascianelli +2
Styled Handwritten Text Generation (HTG) has recently received attention from the computer vision and document analysis communities, which have developed several solutions, either…
Merging and Splitting Diffusion Paths for Semantically Coherent Panoramas
Fabio Quattrini, Vittorio Pippi, Silvia Cascianelli +1
Diffusion models have become the State-of-the-Art for text-to-image generation, and increasing research effort has been dedicated to adapting the inference process of pretrained di…