PG2021 Short Papers, Posters, and Work-in-Progress Papers
Permanent URI for this collection
Browse
Browsing PG2021 Short Papers, Posters, and Work-in-Progress Papers by Author "Qin, Hong"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item 3D-CariNet: End-to-end 3D Caricature Generation from Natural Face Images with Differentiable Renderer(The Eurographics Association, 2021) Huang, Meijia; Dai, Ju; Pan, Junjun; Bai, Junxuan; Qin, Hong; Lee, Sung-Hee and Zollmann, Stefanie and Okabe, Makoto and Wünsche, BurkhardCaricatures are an artistic representation of human faces to express satire and humor. Caricature generation of human faces is a hotspot in CG research. Previous work mainly focuses on 2D caricatures generation from face photos or 3D caricature reconstruction from caricature images. In this paper, we propose a novel end-to-end method to directly generate personalized 3D caricatures from a single natural face image. It can create not only exaggerated geometric shapes, but also heterogeneous texture styles. Firstly, we construct a synthetic dataset containing matched data pairs composed of face photos, caricature images, and 3D caricatures. Then, we design a graph convolutional autoencoder to build a non-linear colored mesh model to learn the shape and texture of 3D caricatures. To make the network end-to-end trainable, we incorporate a differentiable renderer to render 3D caricatures into caricature images inversely. Experiments demonstrate that our method can achieve 3D caricature generation with various texture styles from face images while maintaining personality characteristics.Item Human Motion Synthesis and Control via Contextual Manifold Embedding(The Eurographics Association, 2021) Zeng, Rui; Dai, Ju; Bai, Junxuan; Pan, Junjun; Qin, Hong; Lee, Sung-Hee and Zollmann, Stefanie and Okabe, Makoto and Wünsche, BurkhardModeling motion dynamics for precise and rapid control by deterministic data-driven models is challenging due to the natural randomness of human motion. To address it, we propose a novel framework for continuous motion control by probabilistic latent variable models. The control is implemented by recurrently querying between historical and target motion states rather than exact motion data. Our model takes a conditional encoder-decoder form in two stages. Firstly, we utilize Gaussian Process Latent Variable Model (GPLVM) to project motion poses to a compact latent manifold. Motion states could be clearly recognized by analyzing on the manifold, such as walking phase and forwarding velocity. Secondly, taking manifold as prior, a Recurrent Neural Network (RNN) encoder makes temporal latent prediction from the previous and control states. An attention module then morphs the prediction by measuring latent similarities to control states and predicted states, thus dynamically preserving contextual consistency. In the end, the GP decoder reconstructs motion states back to motion frames. Experiments on walking datasets show that our model is able to maintain motion states autoregressively while performing rapid and smooth transitions for the control.