Description: Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text
nerf (144) d-nerf (50) nerfies (49)
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
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 adversaria
Make-It-Vivid supports efficient characters production and animation under text or video input.