arXiv subjects

Shihong Xia

Publications and source records attributed to Shihong Xia.

24 records · Page 2Linked to original sources

arXiv2018

Learning Bidirectional LSTM Networks for Synthesizing 3D Mesh Animation Sequences

In this paper, we present a novel method for learning to synthesize 3D mesh animation sequences with long short-term memory (LSTM) blocks and mesh-based convolutional neural networks (CNNs). Synthesizing realistic 3D mesh animation sequences is a challenging and important task in computer animation. To achieve this, researchers have long been focusing on shape analysis to develop new interpolation and extrapolation techniques. However, such techniques have limited learning capabilities and therefore can produce unrealistic animation. Deep architectures that operate directly on mesh sequences remain unexplored, due to the following major barriers: meshes with irregular triangles, sequences containing rich temporal information and flexible deformations. To address these, we utilize convolutional neural networks defined on triangular meshes along with a shape deformation representation to extract useful features, followed by LSTM cells that iteratively process the features. To allow completion of a missing mesh sequence from given endpoints, we propose a new weight-shared bidirectional structure. The bidirectional generation loss also helps mitigate error accumulation over iterations. Benefiting from all these technical advances, our approach outperforms existing methods in sequence prediction and completion both qualitatively and quantitatively. Moreover, this network can also generate follow-up frames conditioned on initial shapes and improve the accuracy as more bootstrap models are provided, which other works in the geometry processing domain cannot achieve.

cs.GR↗

arXiv2018

Combining Recurrent Neural Networks and Adversarial Training for Human Motion Synthesis and Control

This paper introduces a new generative deep learning network for human motion synthesis and control. Our key idea is to combine recurrent neural networks (RNNs) and adversarial training for human motion modeling. We first describe an efficient method for training a RNNs model from prerecorded motion data. We implement recurrent neural networks with long short-term memory (LSTM) cells because they are capable of handling nonlinear dynamics and long term temporal dependencies present in human motions. Next, we train a refiner network using an adversarial loss, similar to Generative Adversarial Networks (GANs), such that the refined motion sequences are indistinguishable from real motion capture data using a discriminative network. We embed contact information into the generative deep learning model to further improve the performance of our generative model. The resulting model is appealing to motion synthesis and control because it is compact, contact-aware, and can generate an infinite number of naturally looking motions with infinite lengths. Our experiments show that motions generated by our deep learning model are always highly realistic and comparable to high-quality motion capture data. We demonstrate the power and effectiveness of our models by exploring a variety of applications, ranging from random motion synthesis, online/offline motion control, and motion filtering. We show the superiority of our generative model by comparison against baseline models.

cs.GR↗

arXiv2018

Variational Autoencoders for Deforming 3D Mesh Models

3D geometric contents are becoming increasingly popular. In this paper, we study the problem of analyzing deforming 3D meshes using deep neural networks. Deforming 3D meshes are flexible to represent 3D animation sequences as well as collections of objects of the same category, allowing diverse shapes with large-scale non-linear deformations. We propose a novel framework which we call mesh variational autoencoders (mesh VAE), to explore the probabilistic latent space of 3D surfaces. The framework is easy to train, and requires very few training examples. We also propose an extended model which allows flexibly adjusting the significance of different latent variables by altering the prior distribution. Extensive experiments demonstrate that our general framework is able to learn a reasonable representation for a collection of deformable shapes, and produce competitive results for a variety of applications, including shape generation, shape interpolation, shape space embedding and shape exploration, outperforming state-of-the-art methods.

cs.GR↗

arXiv2018

Cascaded 3D Full-body Pose Regression from Single Depth Image at 100 FPS

There are increasing real-time live applications in virtual reality, where it plays an important role in capturing and retargetting 3D human pose. But it is still challenging to estimate accurate 3D pose from consumer imaging devices such as depth camera. This paper presents a novel cascaded 3D full-body pose regression method to estimate accurate pose from a single depth image at 100 fps. The key idea is to train cascaded regressors based on Gradient Boosting algorithm from pre-recorded human motion capture database. By incorporating hierarchical kinematics model of human pose into the learning procedure, we can directly estimate accurate 3D joint angles instead of joint positions. The biggest advantage of this model is that the bone length can be preserved during the whole 3D pose estimation procedure, which leads to more effective features and higher pose estimation accuracy. Our method can be used as an initialization procedure when combining with tracking methods. We demonstrate the power of our method on a wide range of synthesized human motion data from CMU mocap database, Human3.6M dataset and real human movements data captured in real time. In our comparison against previous 3D pose estimation methods and commercial system such as Kinect 2017, we achieve the state-of-the-art accuracy.

cs.GR↗

arXiv2017

Mesh-based Autoencoders for Localized Deformation Component Analysis

Spatially localized deformation components are very useful for shape analysis and synthesis in 3D geometry processing. Several methods have recently been developed, with an aim to extract intuitive and interpretable deformation components. However, these techniques suffer from fundamental limitations especially for meshes with noise or large-scale deformations, and may not always be able to identify important deformation components. In this paper we propose a novel mesh-based autoencoder architecture that is able to cope with meshes with irregular topology. We introduce sparse regularization in this framework, which along with convolutional operations, helps localize deformations. Our framework is capable of extracting localized deformation components from mesh data sets with large-scale deformations and is robust to noise. It also provides a nonlinear approach to reconstruction of meshes using the extracted basis, which is more effective than the current linear combination approach. Extensive experiments show that our method outperforms state-of-the-art methods in both qualitative and quantitative evaluations.

cs.GR↗

arXiv2017

Sparse Data Driven Mesh Deformation

Example-based mesh deformation methods are powerful tools for realistic shape editing. However, existing techniques typically combine all the example deformation modes, which can lead to overfitting, i.e. using a overly complicated model to explain the user-specified deformation. This leads to implausible or unstable deformation results, including unexpected global changes outside the region of interest. To address this fundamental limitation, we propose a sparse blending method that automatically selects a smaller number of deformation modes to compactly describe the desired deformation. This along with a suitably chosen deformation basis including spatially localized deformation modes leads to significant advantages, including more meaningful, reliable, and efficient deformations because fewer and localized deformation modes are applied. To cope with large rotations, we develop a simple but effective representation based on polar decomposition of deformation gradients, which resolves the ambiguity of large global rotations using an as-consistent-as-possible global optimization. This simple representation has a closed form solution for derivatives, making it efficient for sparse localized representation and thus ensuring interactive performance. Experimental results show that our method outperforms state-of-the-art data-driven mesh deformation methods, for both quality of results and efficiency.

cs.GR↗