ReCorD: Reasoning and Correcting Diffusion for HOI Generation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jiang-Lin, Jian-Yu, Huang, Kang-Yang, Lo, Ling, Huang, Yi-Ning, Lin, Terence, Wu, Jhih-Ciang, Shuai, Hong-Han, Cheng, Wen-Huang
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914886688178176
author Jiang-Lin, Jian-Yu
Huang, Kang-Yang
Lo, Ling
Huang, Yi-Ning
Lin, Terence
Wu, Jhih-Ciang
Shuai, Hong-Han
Cheng, Wen-Huang
author_facet Jiang-Lin, Jian-Yu
Huang, Kang-Yang
Lo, Ling
Huang, Yi-Ning
Lin, Terence
Wu, Jhih-Ciang
Shuai, Hong-Han
Cheng, Wen-Huang
contents Diffusion models revolutionize image generation by leveraging natural language to guide the creation of multimedia content. Despite significant advancements in such generative models, challenges persist in depicting detailed human-object interactions, especially regarding pose and object placement accuracy. We introduce a training-free method named Reasoning and Correcting Diffusion (ReCorD) to address these challenges. Our model couples Latent Diffusion Models with Visual Language Models to refine the generation process, ensuring precise depictions of HOIs. We propose an interaction-aware reasoning module to improve the interpretation of the interaction, along with an interaction correcting module to refine the output image for more precise HOI generation delicately. Through a meticulous process of pose selection and object positioning, ReCorD achieves superior fidelity in generated images while efficiently reducing computational requirements. We conduct comprehensive experiments on three benchmarks to demonstrate the significant progress in solving text-to-image generation tasks, showcasing ReCorD's ability to render complex interactions accurately by outperforming existing methods in HOI classification score, as well as FID and Verb CLIP-Score. Project website is available at https://alberthkyhky.github.io/ReCorD/ .
format Preprint
id arxiv_https___arxiv_org_abs_2407_17911
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ReCorD: Reasoning and Correcting Diffusion for HOI Generation
Jiang-Lin, Jian-Yu
Huang, Kang-Yang
Lo, Ling
Huang, Yi-Ning
Lin, Terence
Wu, Jhih-Ciang
Shuai, Hong-Han
Cheng, Wen-Huang
Multimedia
Artificial Intelligence
Computer Vision and Pattern Recognition
Diffusion models revolutionize image generation by leveraging natural language to guide the creation of multimedia content. Despite significant advancements in such generative models, challenges persist in depicting detailed human-object interactions, especially regarding pose and object placement accuracy. We introduce a training-free method named Reasoning and Correcting Diffusion (ReCorD) to address these challenges. Our model couples Latent Diffusion Models with Visual Language Models to refine the generation process, ensuring precise depictions of HOIs. We propose an interaction-aware reasoning module to improve the interpretation of the interaction, along with an interaction correcting module to refine the output image for more precise HOI generation delicately. Through a meticulous process of pose selection and object positioning, ReCorD achieves superior fidelity in generated images while efficiently reducing computational requirements. We conduct comprehensive experiments on three benchmarks to demonstrate the significant progress in solving text-to-image generation tasks, showcasing ReCorD's ability to render complex interactions accurately by outperforming existing methods in HOI classification score, as well as FID and Verb CLIP-Score. Project website is available at https://alberthkyhky.github.io/ReCorD/ .
title ReCorD: Reasoning and Correcting Diffusion for HOI Generation
topic Multimedia
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.17911