Interact3D: Compositional 3D Generation of Interactive Objects

TL;DR

Interact3D introduces a novel framework for generating physically plausible, collision-aware 3D composite objects from single images, effectively preserving spatial relationships and geometric details through a multi-stage, refinement-driven process.

Contribution

The paper presents a new two-stage composition pipeline with a VLM-guided refinement strategy for 3D object composition, addressing occlusion and spatial relationship preservation challenges.

Findings

Produces collision-aware, high-fidelity 3D compositions

Improves geometric detail preservation in occluded regions

Demonstrates effective spatial relationship maintenance

Abstract

Recent breakthroughs in 3D generation have enabled the synthesis of high-fidelity individual assets. However, generating 3D compositional objects from single images--particularly under occlusions--remains challenging. Existing methods often degrade geometric details in hidden regions and fail to preserve the underlying object-object spatial relationships (OOR). We present a novel framework Interact3D designed to generate physically plausible interacting 3D compositional objects. Our approach first leverages advanced generative priors to curate high-quality individual assets with a unified 3D guidance scene. To physically compose these assets, we then introduce a robust two-stage composition pipeline. Based on the 3D guidance scene, the primary object is anchored through precise global-to-local geometric alignment (registration), while subsequent geometries are integrated using a differentiable Signed Distance Field (SDF)-based optimization that explicitly penalizes geometry intersections. To reduce challenging collisions, we further deploy a closed-loop, agentic refinement strategy. A Vision-Language Model (VLM) autonomously analyzes multi-view renderings of the composed scene, formulates targeted corrective prompts, and guides an image editing module to iteratively self-correct the generation pipeline. Extensive experiments demonstrate that Interact3D successfully produces promising collsion-aware compositions with improved geometric fidelity and consistent spatial relationships.