Papers
arxiv:2507.16813

HOComp: Interaction-Aware Human-Object Composition

Published on Jul 22
· Submitted by LeoLau on Jul 23
Authors:
,
,

Abstract

HOComp, a novel method using MLLMs and appearance preservation techniques, generates harmonious human-object interactions with consistent appearances in images.

AI-generated summary

While existing image-guided composition methods may help insert a foreground object onto a user-specified region of a background image, achieving natural blending inside the region with the rest of the image unchanged, we observe that these existing methods often struggle in synthesizing seamless interaction-aware compositions when the task involves human-object interactions. In this paper, we first propose HOComp, a novel approach for compositing a foreground object onto a human-centric background image, while ensuring harmonious interactions between the foreground object and the background person and their consistent appearances. Our approach includes two key designs: (1) MLLMs-driven Region-based Pose Guidance (MRPG), which utilizes MLLMs to identify the interaction region as well as the interaction type (e.g., holding and lefting) to provide coarse-to-fine constraints to the generated pose for the interaction while incorporating human pose landmarks to track action variations and enforcing fine-grained pose constraints; and (2) Detail-Consistent Appearance Preservation (DCAP), which unifies a shape-aware attention modulation mechanism, a multi-view appearance loss, and a background consistency loss to ensure consistent shapes/textures of the foreground and faithful reproduction of the background human. We then propose the first dataset, named Interaction-aware Human-Object Composition (IHOC), for the task. Experimental results on our dataset show that HOComp effectively generates harmonious human-object interactions with consistent appearances, and outperforms relevant methods qualitatively and quantitatively.

Community

Paper author Paper submitter
edited Jul 23
Paper author Paper submitter

Paper author Paper submitter

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2507.16813 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2507.16813 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2507.16813 in a Space README.md to link it from this page.

Collections including this paper 1