Extensive ablation studies and comparisons with state-of-the-art methods demonstrate that our method can generate high-fidelity 3D head geometries with the guidance of these priors.
Optical flow is inherently a 2D search problem, and thus the computational complexity grows quadratically with respect to the search window, making large displacements matching infeasible for high-resolution images.
In this paper, we propose StereoPIFu, which integrates the geometric constraints of stereo vision with implicit function representation of PIFu, to recover the 3D shape of the clothed human from a pair of low-cost rectified images.
Generating high-fidelity talking head video by fitting with the input audio sequence is a challenging problem that receives considerable attentions recently.
Although convolutional neural networks have achieved remarkable success in analyzing 2D images/videos, it is still non-trivial to apply the well-developed 2D techniques in regular domains to the irregular 3D point cloud data.
Learning non-rigid registration in an end-to-end manner is challenging due to the inherent high degrees of freedom and the lack of labeled training data.
no code implementations • 11 Nov 2020 • Fengquan Wu, Jixia Li, Shifan Zuo, Xuelei Chen, Santanu Das, John P. Marriner, Trevor M. Oxholm, Anh Phan, Albert Stebbins, Peter T. Timbie, Reza Ansari, Jean-Eric Campagne, Zhiping Chen, Yanping Cong, Qizhi Huang, Yichao Li, Tao Liu, Yingfeng Liu, Chenhui Niu, Calvin Osinga, Olivier Perdereau, Jeffrey B. Peterson, Huli Shi, Gage Siebert, ShiJie Sun, Haijun Tian, Gregory S. Tucker, Qunxiong Wang, Rongli Wang, Yougang Wang, Yanlin Wu, Yidong Xu, Kaifeng Yu, Zijie Yu, Jiao Zhang, Juyong Zhang, Jialu Zhu
Combining all the baselines, we make maps around bright sources and show that the array behaves as expected.
Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics
Side information of items, e. g., images and text description, has shown to be effective in contributing to accurate recommendations.
The problem of deforming an artist-drawn caricature according to a given normal face expression is of interest in applications such as social media, animation and entertainment.
On challenging datasets with noises and partial overlaps, we achieve similar or better accuracy than Sparse ICP while being at least an order of magnitude faster.
Therefore, they may not be effective in capturing the global dependency between words, and tend to be easily biased by noise review information.
Graph neural networks (GNN) have recently been applied to exploit knowledge graph (KG) for recommendation.
Mesh is a powerful data structure for 3D shapes.
To this end, we first build a dataset with various styles of 2D caricatures and their corresponding 3D shapes, and then build a parametric model on vertex based deformation space for 3D caricature face.
Despite the remarkable progress made by learning based stereo matching algorithms, one key challenge remains unsolved.
Ranked #1 on Stereo Disparity Estimation on Scene Flow
Imperfect data (noise, outliers and partial overlap) and high degrees of freedom make non-rigid registration a classical challenging problem in computer vision.
In this paper, we consider the problem to automatically reconstruct garment and body shapes from a single near-front view RGB image.
Recently, 3D face reconstruction from a single image has achieved great success with the help of deep learning and shape prior knowledge, but they often fail to produce accurate geometry details.
In this paper, we propose an end-to-end deep neural network model to generate high-quality 3D caricature with a simple face photo as input.
In this paper, we address this problem by proposing a deep neural network model that takes an audio signal A of a source person and a very short video V of a target person as input, and outputs a synthesized high-quality talking face video with personalized head pose (making use of the visual information in V), expression and lip synchronization (by considering both A and V).
Interactive recommender systems that enable the interactions between users and the recommender system have attracted increasing research attentions.
Caricature is an abstraction of a real person which distorts or exaggerates certain features, but still retains a likeness.
Human bodies exhibit various shapes for different identities or poses, but the body shape has certain similarities in structure and thus can be embedded in a low-dimensional space.
In this paper, we propose a new learning based method consisting of DepthNet, PoseNet and Region Deformer Networks (RDN) to estimate depth from unconstrained monocular videos without ground truth supervision.
Teleconference or telepresence based on virtual reality (VR) headmount display (HMD) device is a very interesting and promising application since HMD can provide immersive feelings for users.
In this paper, we propose a parallel and scalable approach for geodesic distance computation on triangle meshes.
Existing convolutional neural network (CNN) based face recognition algorithms typically learn a discriminative feature mapping, using a loss function that enforces separation of features from different classes and/or aggregation of features within the same class.
Although 3D scanned data contain accurate geometric information of face shapes, the capture system is expensive and such datasets usually contain a small number of subjects.
Employing deep learning-based approaches for fine-grained facial expression analysis, such as those involving the estimation of Action Unit (AU) intensities, is difficult due to the lack of a large-scale dataset of real faces with sufficiently diverse AU labels for training.
Extensive experimental results demonstrate the effectiveness of the proposed filter for various geometry processing applications such as mesh denoising, geometry feature enhancement, and texture color filtering.
The deep face feature (DFF) is trained using correspondence between face images rendered from different views.
With the powerfulness of convolution neural networks (CNN), CNN based face reconstruction has recently shown promising performance in reconstructing detailed face shape from 2D face images.
3D face reconstruction from a single image is a classical and challenging problem, with wide applications in many areas.
As a result, our approach is robust, stable and is able to efficiently recover high quality of surface details even starting with a coarse MVS.