REVIEW 5 cited by
ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
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.
Forward citations
Cited by 5 Pith papers
-
PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models
A multi-view diffusion pipeline that segments 3D objects into parts, completes occluded or invisible parts, and reconstructs them into a compositional 3D asset.
-
MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation
MIDI extends pre-trained image-to-3D object generators to multi-instance diffusion with a multi-instance attention mechanism, producing spatially coherent 3D scenes from a single image in one pass.
-
ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary
A training-free pipeline that generates editable 3D scenes from text by using a generated 2D image as an intermediary to extract object shapes, appearances, positions, and poses.
-
PhyCAGE: Physically Plausible Compositional 3D Asset Generation from a Single Image
A single-image pipeline that generates physically plausible compositional 3D Gaussian Splatting assets by using a physics simulator as a gradient-driven optimizer.
-
Material Anything: Generating Materials for Any 3D Object via Diffusion
Material Anything is a unified diffusion pipeline that generates PBR material maps (albedo, roughness, metallic, bump) for arbitrary 3D meshes using confidence masks to handle varying texture and lighting conditions.
Discussion (0). Continue with ORCID to comment.