ThemeStation: Generating Theme-Aware 3D Assets from Few Exemplars
Zhenwei Wang, Tengfei Wang, Gerhard Hancke, Ziwei Liu, Rynson W.H. Lau

TL;DR
ThemeStation is a new method for generating diverse, theme-consistent 3D assets from few exemplars, combining a two-stage process with a novel dual score distillation loss to improve quality and diversity.
Contribution
It introduces a two-stage framework with dual score distillation loss for theme-aware 3D asset generation from limited exemplars, advancing customization and diversity.
Findings
Outperforms prior methods in quality and diversity of generated 3D assets.
Enables controllable 3D-to-3D generation applications.
Validated by extensive experiments and user studies.
Abstract
Real-world applications often require a large gallery of 3D assets that share a consistent theme. While remarkable advances have been made in general 3D content creation from text or image, synthesizing customized 3D assets following the shared theme of input 3D exemplars remains an open and challenging problem. In this work, we present ThemeStation, a novel approach for theme-aware 3D-to-3D generation. ThemeStation synthesizes customized 3D assets based on given few exemplars with two goals: 1) unity for generating 3D assets that thematically align with the given exemplars and 2) diversity for generating 3D assets with a high degree of variations. To this end, we design a two-stage framework that draws a concept image first, followed by a reference-informed 3D modeling stage. We propose a novel dual score distillation (DSD) loss to jointly leverage priors from both the input exemplars…
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.
Taxonomy
TopicsHuman Motion and Animation · Video Analysis and Summarization · Computer Graphics and Visualization Techniques
MethodsALIGN
