Can I read Generating Coherent Sequences of Visual Illustrations for Real-World Manual Tasks on EtoBox?

Generating Coherent Sequences of Visual Illustrations for Real-World Manual Tasks by Bordalo, João; Ramos, Vasco; Valério, Rodrigo; Glória-Silva, Diogo; Bitton, Yonatan; Yarom, Michal; Szpektor, Idan; Magalhaes, Joao is a scholarly article available to read on EtoBox.

What is Generating Coherent Sequences of Visual Illustrations for Real-World Manual Tasks about?

Multistep instructions, such as recipes and how-to guides, greatly benefit from visual aids, such as a series of images that accompany the instruction steps. While Large Language Models (LLMs) have become adept at generating coherent textual steps, Large Vision/Language Models (LVLMs) are less capable of generating accompanying image sequences. The most challenging aspect is that each generated image needs to adhere to the relevant textual step instruction, as well as be visually consistent with earlier images in the sequence. To address this problem, we propose an approach for generating consistent image sequences, which integrates a Latent Diffusion Model (LDM) with an LLM to transform the sequence into a caption to maintain the semantic coherence of the sequence. In addition, to maintain the visual coherence of the image sequence, we introduce a copy mechanism to initialise reverse diffusion processes with a latent vector iteration from a previously generated image from a relevant step. Both strategies will condition the reverse diffusion process on the sequence of instruction steps and tie the contents of the current image to previous instruction steps and corresponding images.

Author

Bordalo, João; Ramos, Vasco; Valério, Rodrigo; Glória-Silva, Diogo; Bitton, Yonatan; Yarom, Michal; Szpektor, Idan; Magalhaes, Joao

Published

2024

Language

EN