Interact-Custom: Customized Human Object Interaction Image Generation
Zhu Xu, Zhaowen Wang, Yuxin Peng, Yang Liu

TL;DR
This paper introduces Interact-Custom, a novel model for customized human-object interaction image generation that preserves identities and controls interaction semantics, addressing dataset limitations and spatial configuration issues.
Contribution
The paper proposes a two-stage model for human-object interaction image generation with explicit spatial modeling and optional background control, advancing fine-grained interaction control.
Findings
Effective interaction control demonstrated on tailored metrics.
Model preserves human and object identities accurately.
High content controllability with background and location inputs.
Abstract
Compositional Customized Image Generation aims to customize multiple target concepts within generation content, which has gained attention for its wild application. Existing approaches mainly concentrate on the target entity's appearance preservation, while neglecting the fine-grained interaction control among target entities. To enable the model of such interaction control capability, we focus on human object interaction scenario and propose the task of Customized Human Object Interaction Image Generation(CHOI), which simultaneously requires identity preservation for target human object and the interaction semantic control between them. Two primary challenges exist for CHOI:(1)simultaneous identity preservation and interaction control demands require the model to decompose the human object into self-contained identity features and pose-oriented interaction features, while the current…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
