InterCoser: Interactive 3D Character Creation with Disentangled Fine-Grained Features

Authors

  • Yi Wang Tianjin University Changzhou Institute of Technology
  • Jian Ma Tianjin University
  • Zhuo Su ByteDance China
  • Guidong Wang ByteDance China
  • Jingyu Yang Tianjin University
  • Yu-Kun Lai Cardiff University
  • Kun Li Tianjin University

DOI:

https://doi.org/10.1609/aaai.v40i12.37993

Abstract

This paper aims to interactively generate and edit disentangled 3D characters based on precise user instructions. Existing methods generate and edit 3D characters via rough and simple editing guidance and entangled representations, making it difficult to achieve precise and comprehensive control over fine-grained local editing and free clothing transfer for characters. To enable accurate and intuitive control over the generation and editing of high-quality 3D characters with freely interchangeable clothing, we propose a novel user-interactive approach for disentangled 3D character creation. Specifically, to achieve precise control over 3D character generation and editing, we introduce two user-friendly interaction approaches: a sketch-based layered character generation/editing method, which supports clothing transfer; and a 3D-proxy-based part-level editing method, enabling fine-grained disentangled editing. To enhance 3D character quality, we propose a 3D Gaussian reconstruction strategy guided by geometric priors, ensuring that 3D characters exhibit detailed local geometry and smooth global surfaces. Extensive experiments on both public datasets and in-the-wild data demonstrate that our approach not only generates high-quality disentangled 3D characters but also supports precise and fine-grained editing through user interaction.

Published

2026-03-14

How to Cite

Wang, Y., Ma, J., Su, Z., Wang, G., Yang, J., Lai, Y.-K., & Li, K. (2026). InterCoser: Interactive 3D Character Creation with Disentangled Fine-Grained Features. Proceedings of the AAAI Conference on Artificial Intelligence, 40(12), 10243–10251. https://doi.org/10.1609/aaai.v40i12.37993

Issue

Section

AAAI Technical Track on Computer Vision IX