Automated Accessory Rigs for Layered 2D Character Illustrations
Jingyi Li, Wilmot Li, Sean Follmer, Maneesh Agrawala
Abstract
Mix-and-match character creation tools enable users to quickly produce 2D character illustrations by combining various predefined accessories, like clothes and hairstyles, which are represented as separate, interchangeable artwork layers. However, these accessory layers are often designed to fit only the default body artwork, so users cannot modify the body without manually updating all the accessory layers as well. To address this issue, we present a method that captures and preserves important relationships between artwork layers so that the predefined accessories adapt with the character’s body. We encode these relationships with four types of constraints that handle common interactions between layers: (1) occlusion, (2) attachment at a point, (3) coincident boundaries, and (4) overlapping regions. A rig is a set of constraints that allow a motion or deformation specified on the body to transfer to the accessory layers. We present an automated algorithm for generating such a rig for each accessory layer, but also allow users to select which constraints to apply to specific accessories. We demonstrate how our system supports a variety of modifications to body shape and pose using artwork from mix-and-match data sets.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext a3f8a2fb-35a3-44ca-9fe2-7cbc26f5c3e2Cited by top-tier papers1
Ask how each one uses itBuilds on2
Related papers
- InterCoser: Interactive 3D Character Creation with Disentangled Fine-Grained FeaturesYi Wang, Jian Ma, Zhuo Su, Guidong Wang et al.AAAI 2026
- APES: Articulated Part Extraction from Sprite SheetsZhan Xu, Matthew Fisher, Yang Zhou, Deepali Aneja et al.CVPR 2022 · 6 citations
- MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image GenerationYuheng Li, Krishna Kumar Singh, Utkarsh Ojha, Yong Jae LeeCVPR 2020
- Learning skeletal articulations with neural blend shapesPeizhuo Li, Kfir Aberman, Rana Hanocka, Libin Liu et al.SIGGRAPH 2021 · 88 citations
- RigAnything: Template-Free Autoregressive Rigging for Diverse 3D AssetsIsabella Liu, Zhan Xu, Wang Yifan, Hao Tan et al.SIGGRAPH 2025 · 11 citations
