Searcharxiv⌕ Search

arXiv subjects

Lizhuang Ma

Publications and source records attributed to Lizhuang Ma.

193 records · Page 11Linked to original sources
arXiv2019

Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution

Point cloud analysis without pose priors is very challenging in real applications, as the orientations of point clouds are often unknown. In this paper, we propose a brand new point-set learning framework PRIN, namely, Pointwise Rotation-Invariant Network, focusing on rotation-invariant feature extraction in point clouds analysis. We construct spherical signals by Density Aware Adaptive Sampling to deal with distorted point distributions in spherical space. In addition, we propose Spherical Voxel Convolution and Point Re-sampling to extract rotation-invariant features for each point. Our network can be applied to tasks ranging from object classification, part segmentation, to 3D feature matching and label alignment. We show that, on the dataset with randomly rotated point clouds, PRIN demonstrates better performance than state-of-the-art methods without any data augmentation. We also provide theoretical analysis for the rotation-invariance achieved by our methods.

cs.CV↗
arXiv2019

FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds

3D object detection from raw and sparse point clouds has been far less treated to date, compared with its 2D counterpart. In this paper, we propose a novel framework called FVNet for 3D front-view proposal generation and object detection from point clouds. It consists of two stages: generation of front-view proposals and estimation of 3D bounding box parameters. Instead of generating proposals from camera images or bird's-eye-view maps, we first project point clouds onto a cylindrical surface to generate front-view feature maps which retains rich information. We then introduce a proposal generation network to predict 3D region proposals from the generated maps and further extrude objects of interest from the whole point cloud. Finally, we present another network to extract the point-wise features from the extruded object points and regress the final 3D bounding box parameters in the canonical coordinates. Our framework achieves real-time performance with 12ms per point cloud sample. Extensive experiments on the 3D detection benchmark KITTI show that the proposed architecture outperforms state-of-the-art techniques which take either camera images or point clouds as input, in terms of accuracy and inference time.

cs.CV↗
arXiv2019

Facial Action Unit Detection Using Attention and Relation Learning

Attention mechanism has recently attracted increasing attentions in the field of facial action unit (AU) detection. By finding the region of interest of each AU with the attention mechanism, AU-related local features can be captured. Most of the existing attention based AU detection works use prior knowledge to predefine fixed attentions or refine the predefined attentions within a small range, which limits their capacity to model various AUs. In this paper, we propose an end-to-end deep learning based attention and relation learning framework for AU detection with only AU labels, which has not been explored before. In particular, multi-scale features shared by each AU are learned firstly, and then both channel-wise and spatial attentions are adaptively learned to select and extract AU-related local features. Moreover, pixel-level relations for AUs are further captured to refine spatial attentions so as to extract more relevant local features. Without changing the network architecture, our framework can be easily extended for AU intensity estimation. Extensive experiments show that our framework (i) soundly outperforms the state-of-the-art methods for both AU detection and AU intensity estimation on the challenging BP4D, DISFA, FERA 2015 and BP4D+ benchmarks, (ii) can adaptively capture the correlated regions of each AU, and (iii) also works well under severe occlusions and large poses.

cs.CV↗
arXiv2018

Efficient Super Resolution Using Binarized Neural Network

Deep convolutional neural networks (DCNNs) have recently demonstrated high-quality results in single-image super-resolution (SR). DCNNs often suffer from over-parametrization and large amounts of redundancy, which results in inefficient inference and high memory usage, preventing massive applications on mobile devices. As a way to significantly reduce model size and computation time, binarized neural network has only been shown to excel on semantic-level tasks such as image classification and recognition. However, little effort of network quantization has been spent on image enhancement tasks like SR, as network quantization is usually assumed to sacrifice pixel-level accuracy. In this work, we explore an network-binarization approach for SR tasks without sacrificing much reconstruction accuracy. To achieve this, we binarize the convolutional filters in only residual blocks, and adopt a learnable weight for each binary filter. We evaluate this idea on several state-of-the-art DCNN-based architectures, and show that binarized SR networks achieve comparable qualitative and quantitative results as their real-weight counterparts. Moreover, the proposed binarized strategy could help reduce model size by 80% when applying on SRResNet, and could potentially speed up inference by 5 times.

cs.CV↗
arXiv2018

Low Rank Matrix Approximation for Geometry Filtering

We propose a robust normal estimation method for both point clouds and meshes using a low rank matrix approximation algorithm. First, we compute a local feature descriptor for each point and find similar, non-local neighbors that we organize into a matrix. We then show that a low rank matrix approximation algorithm can robustly estimate normals for both point clouds and meshes. Furthermore, we provide a new filtering method for point cloud data to smooth the position data to fit the estimated normals. We show applications of our method to point cloud filtering, point set upsampling, surface reconstruction, mesh denoising, and geometric texture removal. Our experiments show that our method outperforms current methods in both visual quality and accuracy.

cs.GR↗
arXiv2018

Deep Multi-Center Learning for Face Alignment

Facial landmarks are highly correlated with each other since a certain landmark can be estimated by its neighboring landmarks. Most of the existing deep learning methods only use one fully-connected layer called shape prediction layer to estimate the locations of facial landmarks. In this paper, we propose a novel deep learning framework named Multi-Center Learning with multiple shape prediction layers for face alignment. In particular, each shape prediction layer emphasizes on the detection of a certain cluster of semantically relevant landmarks respectively. Challenging landmarks are focused firstly, and each cluster of landmarks is further optimized respectively. Moreover, to reduce the model complexity, we propose a model assembling method to integrate multiple shape prediction layers into one shape prediction layer. Extensive experiments demonstrate that our method is effective for handling complex occlusions and appearance variations with real-time performance. The code for our method is available at https://github.com/ZhiwenShao/MCNet-Extension.

cs.CV↗
arXiv2018

Light Transport Simulation via Generalized Multiple Importance Sampling

Multiple importance sampling (MIS) is employed to reduce variance of estimators, but when sampling and weighting are not suitable to the integrand, the estimators would have extra variance. Therefore, robust light transport simulation algorithms based on Monte Carlo sampling for different types of scenes are still uncompleted. In this paper, we address this problem by present a general method, named generalized multiple importance sampling (GMIS), to enhance the robustness of light transport simulation based on MIS. GMIS combines different sampling techniques and weighting functions, extending MIS to a more generalized framework. Meanwhile, we implement the GMIS in common renderers and illustrate how it increase the robustness of light transport simulation. Experiments show that, by applying GMIS, we obtain better convergence performance and lower variance, and increase the rendering of ambient light and specular shadow effects apparently.

cs.GR↗
arXiv2018

Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment

Facial action unit (AU) detection and face alignment are two highly correlated tasks since facial landmarks can provide precise AU locations to facilitate the extraction of meaningful local features for AU detection. Most existing AU detection works often treat face alignment as a preprocessing and handle the two tasks independently. In this paper, we propose a novel end-to-end deep learning framework for joint AU detection and face alignment, which has not been explored before. In particular, multi-scale shared features are learned firstly, and high-level features of face alignment are fed into AU detection. Moreover, to extract precise local features, we propose an adaptive attention learning module to refine the attention map of each AU adaptively. Finally, the assembled local features are integrated with face alignment features and global features for AU detection. Experiments on BP4D and DISFA benchmarks demonstrate that our framework significantly outperforms the state-of-the-art methods for AU detection.

cs.CV↗
arXiv2018

DRPose3D: Depth Ranking in 3D Human Pose Estimation

In this paper, we propose a two-stage depth ranking based method (DRPose3D) to tackle the problem of 3D human pose estimation. Instead of accurate 3D positions, the depth ranking can be identified by human intuitively and learned using the deep neural network more easily by solving classification problems. Moreover, depth ranking contains rich 3D information. It prevents the 2D-to-3D pose regression in two-stage methods from being ill-posed. In our method, firstly, we design a Pairwise Ranking Convolutional Neural Network (PRCNN) to extract depth rankings of human joints from images. Secondly, a coarse-to-fine 3D Pose Network(DPNet) is proposed to estimate 3D poses from both depth rankings and 2D human joint locations. Additionally, to improve the generality of our model, we introduce a statistical method to augment depth rankings. Our approach outperforms the state-of-the-art methods in the Human3.6M benchmark for all three testing protocols, indicating that depth ranking is an essential geometric feature which can be learned to improve the 3D pose estimation.

cs.CV↗
arXiv2018

Mask-aware Photorealistic Face Attribute Manipulation

The task of face attribute manipulation has found increasing applications, but still remains challenging with the requirement of editing the attributes of a face image while preserving its unique details. In this paper, we choose to combine the Variational AutoEncoder (VAE) and Generative Adversarial Network (GAN) for photorealistic image generation. We propose an effective method to modify a modest amount of pixels in the feature maps of an encoder, changing the attribute strength continuously without hindering global information. Our training objectives of VAE and GAN are reinforced by the supervision of face recognition loss and cycle consistency loss for faithful preservation of face details. Moreover, we generate facial masks to enforce background consistency, which allows our training to focus on manipulating the foreground face rather than background. Experimental results demonstrate our method, called Mask-Adversarial AutoEncoder (M-AAE), can generate high-quality images with changing attributes and outperforms prior methods in detail preservation.

cs.CV↗
arXiv2018

Multi-Scale Video Frame-Synthesis Network with Transitive Consistency Loss

Traditional approaches to interpolate/extrapolate frames in a video sequence require accurate pixel correspondences between images, e.g., using optical flow. Their results stem on the accuracy of optical flow estimation, and could generate heavy artifacts when flow estimation failed. Recently methods using auto-encoder has shown impressive progress, however they are usually trained for specific interpolation/extrapolation settings and lack of flexibility and In order to reduce these limitations, we propose a unified network to parameterize the interest frame position and therefore infer interpolate/extrapolate frames within the same framework. To achieve this, we introduce a transitive consistency loss to better regularize the network. We adopt a multi-scale structure for the network so that the parameters can be shared across multi-layers. Our approach avoids expensive global optimization of optical flow methods, and is efficient and flexible for video interpolation/extrapolation applications. Experimental results have shown that our method performs favorably against state-of-the-art methods.

cs.CV↗
arXiv2016

Learning deep representation from coarse to fine for face alignment

In this paper, we propose a novel face alignment method that trains deep convolutional network from coarse to fine. It divides given landmarks into principal subset and elaborate subset. We firstly keep a large weight for principal subset to make our network primarily predict their locations while slightly take elaborate subset into account. Next the weight of principal subset is gradually decreased until two subsets have equivalent weights. This process contributes to learn a good initial model and search the optimal model smoothly to avoid missing fairly good intermediate models in subsequent procedures. On the challenging COFW dataset [1], our method achieves 6.33% mean error with a reduction of 21.37% compared with the best previous result [2].

cs.CV↗