arXiv subjects

Juyong Zhang

Publications and source records attributed to Juyong Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2022

The Electromagnetic Characteristics of the Tianlai Cylindrical Pathfinder Array

A great challenge for 21 cm intensity mapping experiments is the strong foreground radiation which is orders of magnitude brighter than the 21cm signal. Removal of the foreground takes advantage of the fact that its frequency spectrum is smooth while the redshifted 21cm signal spectrum is stochastic. However, a complication is the non-smoothness of the instrument response. This paper describes the electromagnetic simulation of the Tianlai cylinder array, a pathfinder for 21 cm intensity mapping experiments. Due to the vast scales involved, a direct simulation requires large amount of computing resources. We have made the simulation practical by using a combination of methods: first simulate a single feed, then an array of feed units, finally with the feed array and a cylindrical reflector together, to obtain the response for a single cylinder. We studied its radiation pattern, bandpass response and the effects of mutual coupling between feed units, and compared the results with observation. Many features seen in the measurement result are well reproduced in the simulation, especially the oscillatory features which are associated with the standing waves on the reflector. The mutual coupling between feed units is quantified with S-parameters, which decrease as the distance between the two feeds increases. Based on the simulated S-parameters, we estimate the correlated noise which has been seen in the visibility data, the results show very good agreement with the data in both magnitude and frequency structures. These results provide useful insights on the problem of 21cm signal extraction for real instruments.

astro-ph.IM↗

arXiv2022

SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video

We propose SelfRecon, a clothed human body reconstruction method that combines implicit and explicit representations to recover space-time coherent geometries from a monocular self-rotating human video. Explicit methods require a predefined template mesh for a given sequence, while the template is hard to acquire for a specific subject. Meanwhile, the fixed topology limits the reconstruction accuracy and clothing types. Implicit representation supports arbitrary topology and can represent high-fidelity geometry shapes due to its continuous nature. However, it is difficult to integrate multi-frame information to produce a consistent registration sequence for downstream applications. We propose to combine the advantages of both representations. We utilize differential mask loss of the explicit mesh to obtain the coherent overall shape, while the details on the implicit surface are refined with the differentiable neural rendering. Meanwhile, the explicit mesh is updated periodically to adjust its topology changes, and a consistency loss is designed to match both representations. Compared with existing methods, SelfRecon can produce high-fidelity surfaces for arbitrary clothed humans with self-supervised optimization. Extensive experimental results demonstrate its effectiveness on real captured monocular videos. The source code is available at https://github.com/jby1993/SelfReconCode.

cs.CV↗

arXiv2022

Neural Points: Point Cloud Representation with Neural Fields for Arbitrary Upsampling

In this paper, we propose Neural Points, a novel point cloud representation and apply it to the arbitrary-factored upsampling task. 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. Therefore, Neural Points contain more shape information and thus have a stronger representation ability. Neural Points is trained with surface containing rich geometric details, such that the trained model has enough expression ability for various shapes. Specifically, we extract deep local features on the points and construct neural fields through the local isomorphism between the 2D parametric domain and the 3D local patch. In the final, local neural fields are integrated together to form the global surface. Experimental results show that Neural Points has powerful representation ability and demonstrate excellent robustness and generalization ability. With Neural Points, we can resample point cloud with arbitrary resolutions, and it outperforms the state-of-the-art point cloud upsampling methods. Code is available at https://github.com/WanquanF/NeuralPoints.

cs.CV↗

arXiv2022

A Survey of Non-Rigid 3D Registration

Non-rigid registration computes an alignment between a source surface with a target surface in a non-rigid manner. In the past decade, with the advances in 3D sensing technologies that can measure time-varying surfaces, non-rigid registration has been applied for the acquisition of deformable shapes and has a wide range of applications. This survey presents a comprehensive review of non-rigid registration methods for 3D shapes, focusing on techniques related to dynamic shape acquisition and reconstruction. In particular, we review different approaches for representing the deformation field, and the methods for computing the desired deformation. Both optimization-based and learning-based methods are covered. We also review benchmarks and datasets for evaluating non-rigid registration methods, and discuss potential future research directions.

cs.CV↗

arXiv2022

Audio-Driven Talking Face Video Generation with Dynamic Convolution Kernels

In this paper, we present a dynamic convolution kernel (DCK) strategy for convolutional neural networks. Using a fully convolutional network with the proposed DCKs, high-quality talking-face video can be generated from multi-modal sources (i.e., unmatched audio and video) in real time, and our trained model is robust to different identities, head postures, and input audios. Our proposed DCKs are specially designed for audio-driven talking face video generation, leading to a simple yet effective end-to-end system. We also provide a theoretical analysis to interpret why DCKs work. Experimental results show that our method can generate high-quality talking-face video with background at 60 fps. Comparison and evaluation between our method and the state-of-the-art methods demonstrate the superiority of our method.

cs.CV↗

arXiv2021

3D-CariGAN: An End-to-End Solution to 3D Caricature Generation from Face Photos

Caricature is a type of artistic style of human faces that attracts considerable attention in the entertainment industry. So far a few 3D caricature generation methods exist and all of them require some caricature information (e.g., a caricature sketch or 2D caricature) as input. This kind of input, however, is difficult to provide by non-professional users. In this paper, we propose an end-to-end deep neural network model that generates high-quality 3D caricatures directly from a normal 2D face photo. 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). To address this challenge, we: (1) build a large dataset of 5,343 3D caricature meshes and use it to establish a PCA model in the 3D caricature shape space; (2) reconstruct a normal full 3D head from the input face photo and use its PCA representation in the 3D caricature shape space to establish correspondences between the input photo and 3D caricature shape; and (3) propose a novel character loss and a novel caricature loss based on previous psychological studies on caricatures. Experiments including a novel two-level user study show that our system can generate high-quality 3D caricatures directly from normal face photos.

cs.CV↗

arXiv2021

Prior-Guided Multi-View 3D Head Reconstruction

Recovery of a 3D head model including the complete face and hair regions is still a challenging problem in computer vision and graphics. In this paper, we consider this problem using only a few multi-view portrait images as input. Previous multi-view stereo methods that have been based, either on optimization strategies or deep learning techniques, suffer from low-frequency geometric structures such as unclear head structures and inaccurate reconstruction in hair regions. To tackle this problem, we propose a prior-guided implicit neural rendering network. Specifically, we model the head geometry with a learnable signed distance field (SDF) and optimize it via an implicit differentiable renderer with the guidance of some human head priors, including the facial prior knowledge, head semantic segmentation information and 2D hair orientation maps. The utilization of these priors can improve the reconstruction accuracy and robustness, leading to a high-quality integrated 3D head model. 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.

cs.CV↗

arXiv2021

GeodesicEmbedding (GE): A High-Dimensional Embedding Approach for Fast Geodesic Distance Queries

In this paper, we develop a novel method for fast geodesic distance queries. The key idea is to embed the mesh into a high-dimensional space, such that the Euclidean distance in the high-dimensional space can induce the geodesic distance in the original manifold surface. However, directly solving the high-dimensional embedding problem is not feasible due to the large number of variables and the fact that the embedding problem is highly nonlinear. We overcome the challenges with two novel ideas. First, instead of taking all vertices as variables, we embed only the saddle vertices, which greatly reduces the problem complexity. We then compute a local embedding for each non-saddle vertex. Second, to reduce the large approximation error resulting from the purely Euclidean embedding, we propose a cascaded optimization approach that repeatedly introduces additional embedding coordinates with a non-Euclidean function to reduce the approximation residual. Using the precomputation data, our approach can determine the geodesic distance between any two vertices in near-constant time. Computational testing results show that our method is more desirable than previous geodesic distance queries methods.

cs.GR↗

arXiv2021

High-Resolution Optical Flow from 1D Attention and Correlation

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 take inspiration from Transformers and propose a new method for high-resolution optical flow estimation with significantly less computation. Specifically, a 1D attention operation is first applied in the vertical direction of the target image, and then a simple 1D correlation in the horizontal direction of the attended image is able to achieve 2D correspondence modeling effect. The directions of attention and correlation can also be exchanged, resulting in two 3D cost volumes that are concatenated for optical flow estimation. The novel 1D formulation empowers our method to scale to very high-resolution input images while maintaining competitive performance. Extensive experiments on Sintel, KITTI and real-world 4K ($2160 \times 3840$) resolution images demonstrated the effectiveness and superiority of our proposed method. Code and models are available at \url{https://github.com/haofeixu/flow1d}.

cs.CV↗

arXiv2021

A Robust Loss for Point Cloud Registration

The performance of surface registration relies heavily on the metric used for the alignment error between the source and target shapes. Traditionally, such a metric is based on the point-to-point or point-to-plane distance from the points on the source surface to their closest points on the target surface, which is susceptible to failure due to instability of the closest-point correspondence. In this paper, we propose a novel metric based on the intersection points between the two shapes and a random straight line, which does not assume a specific correspondence. We verify the effectiveness of this metric by extensive experiments, including its direct optimization for a single registration problem as well as unsupervised learning for a set of registration problems. The results demonstrate that the algorithms utilizing our proposed metric outperforms the state-of-the-art optimization-based and unsupervised learning-based methods.

cs.CV↗

arXiv2021

AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis

Generating high-fidelity talking head video by fitting with the input audio sequence is a challenging problem that receives considerable attentions recently. In this paper, we address this problem with the aid of neural scene representation networks. Our method is completely different from existing methods that rely on intermediate representations like 2D landmarks or 3D face models to bridge the gap between audio input and video output. Specifically, the feature of input audio signal is directly fed into a conditional implicit function to generate a dynamic neural radiance field, from which a high-fidelity talking-head video corresponding to the audio signal is synthesized using volume rendering. Another advantage of our framework is that not only the head (with hair) region is synthesized as previous methods did, but also the upper body is generated via two individual neural radiance fields. Experimental results demonstrate that our novel framework can (1) produce high-fidelity and natural results, and (2) support free adjustment of audio signals, viewing directions, and background images. Code is available at https://github.com/YudongGuo/AD-NeRF.

cs.CV↗

arXiv2021

The Tianlai Dish Pathfinder Array: design, operation and performance of a prototype transit radio interferometer

The Tianlai Dish Pathfinder Array is a radio interferometer designed to test techniques for 21~cm intensity mapping in the post-reionization universe as a means for measuring large-scale cosmic structure. It performs drift scans of the sky at constant declination. We describe the design, calibration, noise level, and stability of this instrument based on the analysis of about $\sim 5 \%$ of 6,200 hours of on-sky observations through October, 2019. Beam pattern determinations using drones and the transit of bright sources are in good agreement, and compatible with electromagnetic simulations. Combining all the baselines, we make maps around bright sources and show that the array behaves as expected. A few hundred hours of observations at different declinations have been used to study the array geometry and pointing imperfections, as well as the instrument noise behaviour. We show that the system temperature is below 80~K for most feed antennas, and that noise fluctuations decrease as expected with integration time, at least up to a few hundred seconds. Analysis of long integrations, from 10 nights of observations of the North Celestial Pole, yielded visibilities with amplitudes of 20-30~mK, consistent with the expected signal from the NCP radio sky with $<10\,$mK precision for $1 ~\mathrm{MHz} \times 1~ \mathrm{min}$ binning. Hi-pass filtering the spectra to remove smooth spectrum signal yields a residual consistent with zero signal at the $0.5\,$mK level.

astro-ph.IM↗

arXiv2021

Recurrent Multi-view Alignment Network for Unsupervised Surface Registration

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. In this paper, we resolve these two challenges simultaneously. First, we propose to represent the non-rigid transformation with a point-wise combination of several rigid transformations. This representation not only makes the solution space well-constrained but also enables our method to be solved iteratively with a recurrent framework, which greatly reduces the difficulty of learning. Second, we introduce a differentiable loss function that measures the 3D shape similarity on the projected multi-view 2D depth images so that our full framework can be trained end-to-end without ground truth supervision. Extensive experiments on several different datasets demonstrate that our proposed method outperforms the previous state-of-the-art by a large margin. The source codes are available at https://github.com/WanquanF/RMA-Net.

cs.CV↗

arXiv2021

StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision

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. First, we introduce the effective voxel-aligned features from a stereo vision-based network to enable depth-aware reconstruction. Moreover, the novel relative z-offset is employed to associate predicted high-fidelity human depth and occupancy inference, which helps restore fine-level surface details. Second, a network structure that fully utilizes the geometry information from the stereo images is designed to improve the human body reconstruction quality. Consequently, our StereoPIFu can naturally infer the human body's spatial location in camera space and maintain the correct relative position of different parts of the human body, which enables our method to capture human performance. Compared with previous works, our StereoPIFu significantly improves the robustness, completeness, and accuracy of the clothed human reconstruction, which is demonstrated by extensive experimental results.

cs.CV↗

arXiv2021

3D Face From X: Learning Face Shape from Diverse Sources

We present a novel method to jointly learn a 3D face parametric model and 3D face reconstruction from diverse sources. Previous methods usually learn 3D face modeling from one kind of source, such as scanned data or in-the-wild images. 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. On the other hand, in-the-wild face images are easily obtained and there are a large number of facial images. However, facial images do not contain explicit geometric information. In this paper, we propose a method to learn a unified face model from diverse sources. Besides scanned face data and face images, we also utilize a large number of RGB-D images captured with an iPhone X to bridge the gap between the two sources. Experimental results demonstrate that with training data from more sources, we can learn a more powerful face model.

cs.CV↗

arXiv2021

Landmark Detection and 3D Face Reconstruction for Caricature using a Nonlinear Parametric Model

Caricature is an artistic abstraction of the human face by distorting or exaggerating certain facial features, while still retains a likeness with the given face. Due to the large diversity of geometric and texture variations, automatic landmark detection and 3D face reconstruction for caricature is a challenging problem and has rarely been studied before. In this paper, we propose the first automatic method for this task by a novel 3D approach. 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. Based on the constructed dataset and the nonlinear parametric model, we propose a neural network based method to regress the 3D face shape and orientation from the input 2D caricature image. Ablation studies and comparison with state-of-the-art methods demonstrate the effectiveness of our algorithm design. Extensive experimental results demonstrate that our method works well for various caricatures. Our constructed dataset, source code and trained model are available at https://github.com/Juyong/CaricatureFace.

cs.CV↗

arXiv2021

Learning Hierarchical Review Graph Representations for Recommendation

The user review data have been demonstrated to be effective in solving different recommendation problems. Previous review-based recommendation methods usually employ sophisticated compositional models, such as Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN), to learn semantic representations from the review data for recommendation. However, these methods mainly capture the local dependency between neighbouring words in a word window, and they treat each review equally. Therefore, they may not be effective in capturing the global dependency between words, and tend to be easily biased by noise review information. In this paper, we propose a novel review-based recommendation model, named Review Graph Neural Network (RGNN). Specifically, RGNN builds a specific review graph for each individual user/item, which provides a global view about the user/item properties to help weaken the biases caused by noise review information. A type-aware graph attention mechanism is developed to learn semantic embeddings of words. Moreover, a personalized graph pooling operator is proposed to learn hierarchical representations of the review graph to form the semantic representation for each user/item. We compared RGNN with state-of-the-art review-based recommendation approaches on two real-world datasets. The experimental results indicate that RGNN consistently outperforms baseline methods, in terms of Mean Square Error (MSE).

cs.IR↗

arXiv2021

Pre-training Graph Transformer with Multimodal Side Information for Recommendation

Side information of items, e.g., images and text description, has shown to be effective in contributing to accurate recommendations. Inspired by the recent success of pre-training models on natural language and images, we propose a pre-training strategy to learn item representations by considering both item side information and their relationships. We relate items by common user activities, e.g., co-purchase, and construct a homogeneous item graph. This graph provides a unified view of item relations and their associated side information in multimodality. We develop a novel sampling algorithm named MCNSampling to select contextual neighbors for each item. The proposed Pre-trained Multimodal Graph Transformer (PMGT) learns item representations with two objectives: 1) graph structure reconstruction, and 2) masked node feature reconstruction. Experimental results on real datasets demonstrate that the proposed PMGT model effectively exploits the multimodality side information to achieve better accuracies in downstream tasks including item recommendation, item classification, and click-through ratio prediction. We also report a case study of testing the proposed PMGT model in an online setting with 600 thousand users.

cs.IR↗