no code implementations • 18 Feb 2017 • Luo Jiang, Juyong Zhang, Bailin Deng, Hao Li, Ligang Liu
3D face reconstruction from a single image is a classical and challenging problem, with wide applications in many areas.
no code implementations • 27 May 2018 • Juyong Zhang, Yuxin Yao, Yue Peng, Hao Yu, Bailin Deng
We propose a novel method to accelerate Lloyd's algorithm for K-Means clustering.
no code implementations • 3 Aug 2017 • Yudong Guo, Juyong Zhang, Jianfei Cai, Boyi Jiang, Jianmin Zheng
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.
no code implementations • 21 Feb 2018 • Zhilei Liu, Guoxian Song, Jianfei Cai, Tat-Jen Cham, Juyong Zhang
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.
no code implementations • 9 Aug 2017 • Boyi Jiang, Juyong Zhang, Bailin Deng, Yudong Guo, Ligang Liu
The deep face feature (DFF) is trained using correspondence between face images rendered from different views.
no code implementations • 24 Nov 2018 • Luo Jiang, Juyong Zhang, Bailin Deng
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.
no code implementations • 21 Jan 2019 • Guoxian Song, Jianfei Cai, Tat-Jen Cham, Jianmin Zheng, Juyong Zhang, Henry Fuchs
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.
no code implementations • CVPR 2014 • Di Xu, Qi Duan, Jianming Zheng, Juyong Zhang, Jianfei Cai, Tat-Jen Cham
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.
no code implementations • 3 Jun 2019 • Yudong Guo, Luo Jiang, Lin Cai, Juyong Zhang
Caricature is an abstraction of a real person which distorts or exaggerates certain features, but still retains a likeness.
no code implementations • 1 Jul 2019 • Yong Liu, Yingtai Xiao, Qiong Wu, Chunyan Miao, Juyong Zhang
Interactive recommender systems that enable the interactions between users and the recommender system have attracted increasing research attentions.
no code implementations • 24 Apr 2020 • Yong liu, Susen Yang, Yinan Zhang, Chunyan Miao, Zaiqing Nie, Juyong Zhang
Therefore, they may not be effective in capturing the global dependency between words, and tend to be easily biased by noise review information.
no code implementations • 24 Apr 2020 • Susen Yang, Yong liu, Yonghui Xu, Chunyan Miao, Min Wu, Juyong Zhang
Graph neural networks (GNN) have recently been applied to exploit knowledge graph (KG) for recommendation.
no code implementations • 12 Aug 2020 • Juyong Zhang, Keyu Chen, Jianmin Zheng
Then we construct correspondences between the two latent spaces guided by geometric and perceptual constraints.
no code implementations • 13 Aug 2020 • Keyu Chen, Jianmin Zheng, Jianfei Cai, Juyong Zhang
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.
no code implementations • 23 Oct 2020 • Yong liu, Susen Yang, Chenyi Lei, Guoxin Wang, Haihong Tang, Juyong Zhang, Aixin Sun, Chunyan Miao
Side information of items, e. g., images and text description, has shown to be effective in contributing to accurate recommendations.
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
no code implementations • 5 Dec 2020 • Qijian Zhang, Junhui Hou, Yue Qian, Juyong Zhang, Ying He
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.
no code implementations • 9 Jul 2021 • Xueying Wang, Yudong Guo, Zhongqi Yang, Juyong Zhang
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.
no code implementations • 25 Sep 2019 • Zhongpai Gao, Juyong Zhang, Yudong Guo, Chao Ma, Guangtao Zhai, Xiaokang Yang
Moreover, the identity and expression representations are entangled in these models, which hurdles many facial editing applications.
no code implementations • 16 Jan 2022 • Zipeng Ye, Mengfei Xia, Ran Yi, Juyong Zhang, Yu-Kun Lai, Xuwei Huang, Guoxin Zhang, Yong-Jin Liu
In this paper, we present a dynamic convolution kernel (DCK) strategy for convolutional neural networks.
no code implementations • 23 Jan 2022 • Zhi Deng, Yang Liu, Hao Pan, Wassim Jabi, Juyong Zhang, Bailin Deng
In this work, we present a novel sketch-based system to bridge the concept design and digital modeling of freeform roof-like shapes represented as planar quadrilateral (PQ) meshes.
no code implementations • 11 Mar 2022 • Bailin Deng, Yuxin Yao, Roberto M. Dyke, Juyong Zhang
Non-rigid registration computes an alignment between a source surface with a target surface in a non-rigid manner.
no code implementations • 4 Oct 2022 • Bo Peng, Jun Hu, Jingtao Zhou, Juyong Zhang
Extensive experimental results on several different datasets demonstrate the effectiveness and efficiency of SelfNeRF to challenging monocular videos.
no code implementations • 28 Feb 2023 • Bo Peng, Jun Hu, Jingtao Zhou, Xuan Gao, Juyong Zhang
To achieve this target, we introduce a continuous and optimizable intrinsic coordinate rather than the original explicit Euclidean coordinate in the hash encoding module of instant-NGP.
no code implementations • 3 Apr 2023 • Dingyun Zhang, Chenglai Zhong, Yudong Guo, Yang Hong, Juyong Zhang
Experiments validate that our controllable digital head engine achieves the state-of-the-art generation visual quality and reconstruction accuracy.
no code implementations • 13 Nov 2023 • Liangchen Li, Juyong Zhang
Since being proposed, Neural Radiance Fields (NeRF) have achieved great success in related tasks, mainly adopting the hierarchical volume sampling (HVS) strategy for volume rendering.
no code implementations • 30 Nov 2023 • Haiyao Xiao, Chenglai Zhong, Xuan Gao, Yudong Guo, Juyong Zhang
Recently, text-guided digital portrait editing has attracted more and more attentions.
no code implementations • 3 Dec 2023 • Jun Xiang, Xuan Gao, Yudong Guo, Juyong Zhang
We propose FlashAvatar, a novel and lightweight 3D animatable avatar representation that could reconstruct a digital avatar from a short monocular video sequence in minutes and render high-fidelity photo-realistic images at 300FPS on a consumer-grade GPU.
no code implementations • 14 Dec 2023 • Xueying Wang, Juyong Zhang
We further model the head geometry in the canonical space with a learnable signed distance field (SDF) and optimize it using the volumetric rendering with the guidance of two-main head priors to improve the reconstruction accuracy and robustness.
no code implementations • 27 Dec 2023 • Kaiwen Song, Xiaoyi Zeng, Chenqu Ren, Juyong Zhang
Existing neural radiance field-based methods can achieve real-time rendering of small scenes on the web platform.
no code implementations • 6 Apr 2024 • Honghu Chen, Yuxin Yao, Juyong Zhang
In this paper, we introduce Neural-ABC, a novel parametric model based on neural implicit functions that can represent clothed human bodies with disentangled latent spaces for identity, clothing, shape, and pose.
no code implementations • 15 Apr 2024 • Xiaoyi Zeng, Kaiwen Song, Leyuan Yang, Bailin Deng, Juyong Zhang
Neural implicit fields have established a new paradigm for scene representation, with subsequent work achieving high-quality real-time rendering.
1 code implementation • 18 Mar 2024 • Yuxin Yao, Siyu Ren, Junhui Hou, Zhi Deng, Juyong Zhang, Wenping Wang
Furthermore, we propose a learnable deformation representation based on the learnable control points and blending weights, which can deform the template surface non-rigidly while maintaining the consistency of the local shape.
1 code implementation • 17 Dec 2022 • Qijian Zhang, Junhui Hou, Yue Qian, Yiming Zeng, Juyong Zhang, Ying He
In this paper, we present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology as a completely regular 2D point geometry image (PGI) structure, in which coordinates of spatial points are captured in colors of image pixels.
1 code implementation • 21 Apr 2020 • Zhongpai Gao, Junchi Yan, Guangtao Zhai, Juyong Zhang, Yiyan Yang, Xiaokang Yang
Mesh is a powerful data structure for 3D shapes.
1 code implementation • 26 Feb 2019 • Haofei Xu, Jianmin Zheng, Jianfei Cai, Juyong Zhang
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.
1 code implementation • 14 Dec 2018 • Jiong Tao, Juyong Zhang, Bailin Deng, Zheng Fang, Yue Peng, Ying He
In this paper, we propose a parallel and scalable approach for geodesic distance computation on triangle meshes.
Graphics
1 code implementation • ICCV 2021 • Zhi Deng, Yuxin Yao, Bailin Deng, Juyong Zhang
The performance of surface registration relies heavily on the metric used for the alignment error between the source and target shapes.
1 code implementation • 14 May 2019 • Boyi Jiang, Juyong Zhang, Jianfei Cai, Jianmin Zheng
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.
1 code implementation • 7 Jun 2022 • Yuxin Yao, Bailin Deng, Weiwei Xu, Juyong Zhang
In this paper, we propose a formulation for robust non-rigid registration based on a globally smooth robust norm for alignment and regularization, which can effectively handle outliers and partial overlaps.
2 code implementations • 10 Dec 2017 • Juyong Zhang, Bailin Deng, Yang Hong, Yue Peng, Wenjie Qin, Ligang Liu
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.
Graphics
1 code implementation • CVPR 2018 • Qianyi Wu, Juyong Zhang, Yu-Kun Lai, Jianmin Zheng, Jianfei Cai
Caricature is an art form that expresses subjects in abstract, simple and exaggerated view.
1 code implementation • 15 Mar 2020 • Zipeng Ye, Mengfei Xia, Yanan sun, Ran Yi, MinJing Yu, Juyong Zhang, Yu-Kun Lai, Yong-Jin Liu
The most challenging issue for our system is that the source domain of face photos (characterized by normal 2D faces) is significantly different from the target domain of 3D caricatures (characterized by 3D exaggerated face shapes and textures).
1 code implementation • ECCV 2020 • Boyi Jiang, Juyong Zhang, Yang Hong, Jinhao Luo, Ligang Liu, Hujun Bao
In this paper, we consider the problem to automatically reconstruct garment and body shapes from a single near-front view RGB image.
1 code implementation • CVPR 2021 • Yang Hong, Juyong Zhang, Boyi Jiang, Yudong Guo, Ligang Liu, Hujun Bao
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.
1 code implementation • ICCV 2021 • Haofei Xu, Jiaolong Yang, Jianfei Cai, Juyong Zhang, Xin Tong
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.
1 code implementation • CVPR 2020 • Xueying Wang, Yudong Guo, Bailin Deng, Juyong Zhang
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.
1 code implementation • CVPR 2021 • Wanquan Feng, Juyong Zhang, Hongrui Cai, Haofei Xu, Junhui Hou, Hujun Bao
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.
1 code implementation • 12 Oct 2022 • Xuan Gao, Chenglai Zhong, Jun Xiang, Yang Hong, Yudong Guo, Juyong Zhang
We present a novel semantic model for human head defined with neural radiance field.
1 code implementation • CVPR 2019 • Zi-Hang Jiang, Qianyi Wu, Keyu Chen, Juyong Zhang
In this paper, we present a novel strategy to design disentangled 3D face shape representation.
1 code implementation • CVPR 2022 • Wanquan Feng, Jin Li, Hongrui Cai, Xiaonan Luo, Juyong Zhang
Different from traditional point cloud representation where each point only represents a position or a local plane in the 3D space, each point in Neural Points represents a local continuous geometric shape via neural fields.
1 code implementation • CVPR 2020 • Yuxin Yao, Bailin Deng, Weiwei Xu, Juyong Zhang
Imperfect data (noise, outliers and partial overlap) and high degrees of freedom make non-rigid registration a classical challenging problem in computer vision.
1 code implementation • CVPR 2022 • Boyi Jiang, Yang Hong, Hujun Bao, Juyong Zhang
Meanwhile, the explicit mesh is updated periodically to adjust its topology changes, and a consistency loss is designed to match both representations.
1 code implementation • 16 Aug 2018 • Yudong Guo, Lin Cai, Juyong Zhang
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.
1 code implementation • CVPR 2022 • Yang Hong, Bo Peng, Haiyao Xiao, Ligang Liu, Juyong Zhang
Different from existing related parametric models, we use the neural radiance fields as a novel 3D proxy instead of the traditional 3D textured mesh, which makes that HeadNeRF is able to generate high fidelity images.
1 code implementation • 15 Jul 2020 • Juyong Zhang, Yuxin Yao, Bailin Deng
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.
1 code implementation • CVPR 2020 • Haofei Xu, Juyong Zhang
Despite the remarkable progress made by learning based stereo matching algorithms, one key challenge remains unsolved.
Ranked #1 on Scene Flow Estimation on Scene Flow
1 code implementation • 30 Jun 2022 • Hongrui Cai, Wanquan Feng, Xuetao Feng, Yan Wang, Juyong Zhang
We propose Neural-DynamicReconstruction (NDR), a template-free method to recover high-fidelity geometry and motions of a dynamic scene from a monocular RGB-D camera.
1 code implementation • 20 Apr 2020 • Hongrui Cai, Yudong Guo, Zhuang Peng, Juyong Zhang
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.
1 code implementation • 24 Feb 2020 • Ran Yi, Zipeng Ye, Juyong Zhang, Hujun Bao, Yong-Jin Liu
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).
1 code implementation • ICCV 2021 • Yudong Guo, Keyu Chen, Sen Liang, Yong-Jin Liu, Hujun Bao, Juyong Zhang
Generating high-fidelity talking head video by fitting with the input audio sequence is a challenging problem that receives considerable attentions recently.