Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text

Abstract

Creating and animating 3D biped cartoon characters is crucial and valuable in various applications. Compared with geometry, the diverse texture design plays an important role in making 3D biped cartoon characters vivid and charming. Therefore, we focus on automatic texture design for cartoon characters based on input instructions. This is challenging for domain-specific requirements and a lack of high-quality data. To address this challenge, we propose Make-It-Vivid, the first attempt to enable high-quality texture generation from text in UV space. We prepare a detailed text-texture paired data for 3D characters by using vision-question-answering agents. Then we customize a pretrained text-to-image model to generate texture map with template structure while preserving the natural 2D image knowledge. Furthermore, to enhance fine-grained details, we propose a novel adversarial learning scheme to shorten the domain gap between original dataset and realistic texture domain. Extensive experiments show that our approach outperforms current texture generation methods, resulting in efficient character texturing and faithful generation with prompts. Besides, we showcase various applications such as out of domain generation and texture stylization. We also provide an efficient generation system for automatic text-guided textured character generation and animation.

Pipeline

Our method takes a pair of data as input including a texture map, corresponding text description P and mesh model M. We finetune the low-rank adaptor ∆θ for pretrained text-to-image diffusion model to generate high quality UV texture. In order to improve the quality and perceptual fidelity of synthetic textures, we introduce adversarial training to enhance the texture details. We leverage synthetic plausible images conditioned by the rendered depth generated by ControlNet as a proxy to guide this adversarial training.

Character Animation

Make-It-Vivid supports efficient characters production and animation under text or video input.

BibTeX

@misc{tang2024makeitvivid,
      title={Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text}, 
      author={Junshu Tang and Yanhong Zeng and Ke Fan and Xuheng Wang and Bo Dai and Kai Chen and Lizhuang Ma},
      year={2024},
      eprint={2403.16897},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}