Hex-dominant mesh generation has recently received increasing attention from researchers and the simulation community due to its robustness compared to pure hex-mesh generation techniques. In this work, we present a first structure-informed simplification framework, aiming to reduce the number of non-hex cells from the hex-dominant meshes. Our framework extracts individual sub-structures via parallel relations from the input hex-dominant mesh, decomposes self-tangent and self-intersecting sub-structures for structure complexity control, and collapses certain sets of edges that are adjacent to particular non-hex cells to remove them. We design a filtering and ranking strategy to select edges and sub-structures for collapsing. To better understand the complexity of sub-structure configurations, we introduced a novel relation graph that captures the connections between edges and between edges and sub-structures. Additionally, we designed a smoothing algorithm for hex-dominant meshes that enhances hex cell quality, even in meshes containing various cell types. We evaluate the effectiveness of our framework by applying it to many hex-dominant meshes produced by three state-of-the-art hex-dominant meshing techniques. Our results achieve various levels of reduction in the number of non-hex cells of the input meshes, affirming the applicability of our framework for improving the hex-dominant meshes.

In this paper we propose a novel conditional generative adversarial network (cGAN) architecture, called S2M-Net, to holistically synthesize realistic three-party conversational animations based on acoustic speech input together with speaker marking (i.e., the speaking time of each interlocutor). Specifically, based on a pre-collected three-party conversational motion dataset, we design and train the S2M-Net for three-party conversational animation synthesis. In the architecture, a generator contains a LSTM encoder to encode a sequence of acoustic speech features to a latent vector that is further fed into a transform unit to transform the latent vector into a gesture kinematics space. Then, the output of this transform unit is fed into a LSTM decoder to generate corresponding three-party conversational gesture kinematics. Meanwhile, a discriminator is implemented to check whether an input sequence of three-party conversational gesture kinematics is real or fake. To evaluate our method, besides quantitative and qualitative evaluations, we also conducted paired comparison user studies to compare it with the state of the art.

Recovering 3D face models from in-the-wild face images has numerous potential applications. However, properly modeling complex lighting effects in reality, including specular lighting, shadows, and occlusions, from a single in-the-wild face image is still considered as a widely open research challenge. In this paper, we propose a convolutional neural network based framework to regress the face model from a single image in the wild. The outputted face model includes dense 3D shape, head pose, expression, diffuse albedo, specular albedo, and the corresponding lighting conditions. Our approach uses novel hybrid loss functions to disentangle face shape identities, expressions, poses, albedos, and lighting. Besides a carefully-designed ablation study, we also conduct direct comparison experiments to show that our method can outperform state-of-art methods both quantitatively and qualitatively.

Realistic 3D facial modeling and animation have been increasingly used in many graphics, animation, and virtual reality applications. However, generating realistic fine-scale wrinkles on 3D faces, in particular, on animated 3D faces, is still a challenging problem that is far away from being resolved. In this article we propose an end-to-end system to automatically augment coarse-scale 3D faces with synthesized fine-scale geometric wrinkles. By formulating the wrinkle generation problem as a supervised generation task, we implicitly model the continuous space of face wrinkles via a compact generative model, such that plausible face wrinkles can be generated through effective sampling and interpolation in the space. We also introduce a complete pipeline to transfer the synthesized wrinkles between faces with different shapes and topologies. Through many experiments, we demonstrate our method can robustly synthesize plausible fine-scale wrinkles on a variety of coarse-scale 3D faces with different shapes and expressions.

In this paper, we propose a novel space that jointly embeds both 2D occluding contours and 3D shapes via a variational autoencoder (VAE) and a volumetric autoencoder. Given a dataset of 3D shapes, we extract their occluding contours via projections from random views and use the occluding contours to train the VAE. Then, the obtained continuous embedding space, where each point is a latent vector that represents an occluding contour, can be used to measure the similarity between occluding contours. After that, the volumetric autoencoder is trained to first map 3D shapes onto the embedding space through a supervised learning process and then decode the merged latent vectors of three occluding contours (from three different views) of a 3D shape to its 3D voxel representation. We conduct various experiments and comparisons to demonstrate the usefulness and effectiveness of our method for sketch-based 3D modeling and shape manipulation applications.