Learning to Generate 3D Stylized Character Expressions from Humans
نویسندگان
چکیده
We present ExprGen, a system to automatically generate 3D stylized character expressions from humans in a perceptually valid and geometrically consistent manner. Our multi-stage deep learning system utilizes the latent variables of human and character expression recognition convolutional neural networks to control a 3D animated character rig. This end-to-end system takes images of human faces and generates the character rig parameters that best match the human’s facial expression. ExprGen generalizes to multiple characters, and allows expression transfer between characters in a semi-supervised manner. Qualitative and quantitative evaluation of our method based on Mechanical Turk tests show the high perceptual accuracy of our expression transfer results.
منابع مشابه
Modeling Stylized Character Expressions via Deep Learning
We propose DeepExpr, a novel expression transfer customized expression transfer approach from human to multiple stylized characters. We first train two Convolutional Neural Networks to recognize the expression of humans and stylized characters independently. Then we utilize a transfer learning technique to learn the mapping from humans to characters to create a shared embedding feature space. T...
متن کاملAppealing Female Avatars from 3D Body Scans: Perceptual Effects of Stylization
Advances in 3D scanning technology allow us to create realistic virtual avatars from full body 3D scan data. However, negative reactions to some realistic computer generated humans suggest that this approach might not always provide the most appealing results. Using styles derived from existing popular character designs, we present a novel automatic stylization technique for body shape and colo...
متن کاملStrokeBank: Automating Personalized Chinese Handwriting Generation
Machine learning techniques have been successfully applied to Chinese character recognition; nonetheless, automatic generation of stylized Chinese handwriting remains a challenge. In this paper, we propose StrokeBank, a novel approach to automating personalized Chinese handwriting generation. We use a semi-supervised algorithm to construct a dictionary of component mappings from a small seeding...
متن کاملFront View vs. Side View of Facial and Postural Expressions of Emotions in a Virtual Character
In 3D virtual environments and social scenes, virtual characters are not always visible from a front view. Nonverbal expressions of emotions should be designed so as to be properly perceived when viewed from multiple angles. Our platform enables the design of facial expressions including 3D expressive wrinkles and 3D postures. It was used to generate stimuli for studying the impact of front ver...
متن کامل