ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance
This addresses the need for high-quality 3D asset creation in applications like AR/VR, though it appears incremental as it builds on prior single-object generation methods by extending them to multi-object scenarios.
The paper tackles the problem of generating complex 3D assets containing multiple objects from a single image, which existing methods struggle with, and presents ComboVerse, a framework that combines multiple 3D models using spatially-aware diffusion guidance to achieve more accurate results, with experiments showing clear improvements over existing methods.
Generating high-quality 3D assets from a given image is highly desirable in various applications such as AR/VR. Recent advances in single-image 3D generation explore feed-forward models that learn to infer the 3D model of an object without optimization. Though promising results have been achieved in single object generation, these methods often struggle to model complex 3D assets that inherently contain multiple objects. In this work, we present ComboVerse, a 3D generation framework that produces high-quality 3D assets with complex compositions by learning to combine multiple models. 1) We first perform an in-depth analysis of this ``multi-object gap'' from both model and data perspectives. 2) Next, with reconstructed 3D models of different objects, we seek to adjust their sizes, rotation angles, and locations to create a 3D asset that matches the given image. 3) To automate this process, we apply spatially-aware score distillation sampling (SSDS) from pretrained diffusion models to guide the positioning of objects. Our proposed framework emphasizes spatial alignment of objects, compared with standard score distillation sampling, and thus achieves more accurate results. Extensive experiments validate ComboVerse achieves clear improvements over existing methods in generating compositional 3D assets.