CMAG: Concept-Scaffolded Retrieval for Marketplace Avatar Generation

TL;DR

CMAG introduces a novel framework for marketplace avatar generation that uses concept scaffolding, visual evidence, and iterative verification to improve retrieval robustness and compositional accuracy from 3D assets.

Contribution

It proposes a new concept-scaffolded retrieval and verification framework that enhances avatar assembly from catalog assets under ambiguous prompts.

Findings

CMAG outperforms strong baselines in retrieval robustness.

It achieves higher compositional correctness in avatar generation.

The framework effectively handles prompt ambiguity and topology constraints.

Abstract

Metaverse platforms rely on creator-driven marketplaces where avatars are assembled from discrete, taxonomy-labeled 3D assets (e.g., tops, bottoms, shoes, accessories) under strict category and topology constraints. While users increasingly expect free-form text control, text-only retrieval is brittle: natural language is ambiguous with respect to platform taxonomies, metadata is often noisy or informal, and independently retrieved components can be stylistically inconsistent or geometrically incompatible. We propose \textbf{CMAG}, a concept-scaffolded retrieval and verified composition framework for marketplace avatar generation. Given a prompt, CMAG first synthesizes an intermediate 3D concept scaffold that disambiguates intent beyond text by providing global spatial and stylistic context. In parallel, a view-aware part discovery module extracts localized visual evidence via prompt decomposition and text-grounded segmentation. A prompt-conditioned taxonomy router enforces category coverage and resolves semantic-to-taxonomic mismatch, after which a hybrid category-wise retriever combines part-based fusion with a concept-residual fallback using feature suppression. Finally, an agentic vision--language model filters and re-ranks candidates across categories and drives an iterative verification loop to assemble prompt-faithful, topologically consistent avatars from catalog assets. We evaluate CMAG on diverse compositional prompts and demonstrate improved retrieval robustness and compositional correctness compared to strong baselines, highlighting the importance of 3D concept scaffolding under prompt ambiguity.