arXiv subjects

Chao Dong

Publications and source records attributed to Chao Dong.

At least 109 records · Page 6Linked to original sources

arXiv2023

OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer

Omnidirectional images (ODIs) have obtained lots of research interest for immersive experiences. Although ODIs require extremely high resolution to capture details of the entire scene, the resolutions of most ODIs are insufficient. Previous methods attempt to solve this issue by image super-resolution (SR) on equirectangular projection (ERP) images. However, they omit geometric properties of ERP in the degradation process, and their models can hardly generalize to real ERP images. In this paper, we propose Fisheye downsampling, which mimics the real-world imaging process and synthesizes more realistic low-resolution samples. Then we design a distortion-aware Transformer (OSRT) to modulate ERP distortions continuously and self-adaptively. Without a cumbersome process, OSRT outperforms previous methods by about 0.2dB on PSNR. Moreover, we propose a convenient data augmentation strategy, which synthesizes pseudo ERP images from plain images. This simple strategy can alleviate the over-fitting problem of large networks and significantly boost the performance of ODISR. Extensive experiments have demonstrated the state-of-the-art performance of our OSRT. Codes and models will be available at https://github.com/Fanghua-Yu/OSRT.

eess.IV↗

arXiv2023

Simultaneous measurement of specific heat and thermal conductivity in pulsed magnetic fields

We report an experimental setup for simultaneously measuring specific heat and thermal conductivity in feedback-controlled pulsed magnetic fields of 50 msec duration at cryogenic temperatures. A stabilized magnetic field pulse obtained by the feedback control, which dramatically improves the thermal stability of the setup and sample, is used in combination with the flash method to obtain absolute values of thermal properties up to 37.2 T in the 2 K to 16 K temperature range. We describe the experimental setup and demonstrate the performance of the present method with measurements on single crystal samples of the geometrically frustrated quantum spin-dimer system SrCu$_2$(BO$_3$)$_2$. Our proof-of-principle results show excellent agreement with data taken using a standard steady-state method, confirming the validity and convenience of the present approach.

cond-mat.str-el↗

arXiv2023

ITstyler: Image-optimized Text-based Style Transfer

Text-based style transfer is a newly-emerging research topic that uses text information instead of style image to guide the transfer process, significantly extending the application scenario of style transfer. However, previous methods require extra time for optimization or text-image paired data, leading to limited effectiveness. In this work, we achieve a data-efficient text-based style transfer method that does not require optimization at the inference stage. Specifically, we convert text input to the style space of the pre-trained VGG network to realize a more effective style swap. We also leverage CLIP's multi-modal embedding space to learn the text-to-style mapping with the image dataset only. Our method can transfer arbitrary new styles of text input in real-time and synthesize high-quality artistic images.

cs.CV↗

arXiv2023

In-situ electrical and thermal transport properties of FeySe1-xTex films with ionic liquid gating

We combine in-situ electrical transport and Seebeck coefficient measurements with the ionic liquid gating technique to investigate superconductivity and the normal state of FeySe1-xTex (FST) films. We find that the pristine FST films feature a non-Fermi liquid temperature dependence of the Seebeck coefficient, i.e., S/T ~ AS lnT, and AS is strongly correlated with the superconducting transition temperature (Tc). Ionic liquid gating significantly raises Tc of FST films, for which the Seebeck coefficient displays a novel scaling behavior and retains the logarithmic temperature dependence. Moreover, a quantitative relationship between the slope of T-linear resistivity (A\r{ho}) and Tc for gated films is observed, i.e., (A\r{ho})1/2 ~ Tc, consistent with previous reports on cuprates and FeSe. The scaling behaviors of AS and A\r{ho} point to a spin-fluctuation-associated transport mechanism in gated FeySe1-xTex superconductors.

cond-mat.supr-con↗

arXiv2022

Mitigating Artifacts in Real-World Video Super-Resolution Models

The recurrent structure is a prevalent framework for the task of video super-resolution, which models the temporal dependency between frames via hidden states. When applied to real-world scenarios with unknown and complex degradations, hidden states tend to contain unpleasant artifacts and propagate them to restored frames. In this circumstance, our analyses show that such artifacts can be largely alleviated when the hidden state is replaced with a cleaner counterpart. Based on the observations, we propose a Hidden State Attention (HSA) module to mitigate artifacts in real-world video super-resolution. Specifically, we first adopt various cheap filters to produce a hidden state pool. For example, Gaussian blur filters are for smoothing artifacts while sharpening filters are for enhancing details. To aggregate a new hidden state that contains fewer artifacts from the hidden state pool, we devise a Selective Cross Attention (SCA) module, in which the attention between input features and each hidden state is calculated. Equipped with HSA, our proposed method, namely FastRealVSR, is able to achieve 2x speedup while obtaining better performance than Real-BasicVSR. Codes will be available at https://github.com/TencentARC/FastRealVSR

cs.CV↗

arXiv2022

Column Generation for Optimization Problems in Communication Networks

Numerous communication networks are emerging to serve the various demands and improve the quality of service. Heterogeneous users have different requirements on quality metrics such as delay and service efficiency. Besides, the networks are equipped with different types and amounts of resources, and how to efficiently optimize the usage of such limited resources to serve more users is the key issue for communication networks. One powerful mathematical optimization mechanism to solve the above issue is column generation (CG), which can deal with the optimization problems with complicating constraints and block angular structures. In this paper, we first review the preliminaries of CG. Further, the branch-and-price (BP) algorithm is elaborated, which is designed by embedding CG into the branch-and-bound scheme to efficiently obtain the optimal solution. The applications of CG and BP in various communication networks are then provided, such as space-air-ground networks and device-to-device networks. In short, our goal is to help readers refine the applications of the CG optimization tool in terms of problem formulation and solution. We also discuss the possible challenges and prospective directions when applying CG in the communication networks.

cs.DS↗

arXiv2022

AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies

Existing correspondence datasets for two-dimensional (2D) cartoon suffer from simple frame composition and monotonic movements, making them insufficient to simulate real animations. In this work, we present a new 2D animation visual correspondence dataset, AnimeRun, by converting open source three-dimensional (3D) movies to full scenes in 2D style, including simultaneous moving background and interactions of multiple subjects. Our analyses show that the proposed dataset not only resembles real anime more in image composition, but also possesses richer and more complex motion patterns compared to existing datasets. With this dataset, we establish a comprehensive benchmark by evaluating several existing optical flow and segment matching methods, and analyze shortcomings of these methods on animation data. Data, code and other supplementary materials are available at https://lisiyao21.github.io/projects/AnimeRun.

cs.CV↗

arXiv2022

Wireless Deep Video Semantic Transmission

In this paper, we design a new class of high-efficiency deep joint source-channel coding methods to achieve end-to-end video transmission over wireless channels. The proposed methods exploit nonlinear transform and conditional coding architecture to adaptively extract semantic features across video frames, and transmit semantic feature domain representations over wireless channels via deep joint source-channel coding. Our framework is collected under the name deep video semantic transmission (DVST). In particular, benefiting from the strong temporal prior provided by the feature domain context, the learned nonlinear transform function becomes temporally adaptive, resulting in a richer and more accurate entropy model guiding the transmission of current frame. Accordingly, a novel rate adaptive transmission mechanism is developed to customize deep joint source-channel coding for video sources. It learns to allocate the limited channel bandwidth within and among video frames to maximize the overall transmission performance. The whole DVST design is formulated as an optimization problem whose goal is to minimize the end-to-end transmission rate-distortion performance under perceptual quality metrics or machine vision task performance metrics. Across standard video source test sequences and various communication scenarios, experiments show that our DVST can generally surpass traditional wireless video coded transmission schemes. The proposed DVST framework can well support future semantic communications due to its video content-aware and machine vision task integration abilities.

cs.CV↗

arXiv2022

Efficient Image Super-Resolution using Vast-Receptive-Field Attention

The attention mechanism plays a pivotal role in designing advanced super-resolution (SR) networks. In this work, we design an efficient SR network by improving the attention mechanism. We start from a simple pixel attention module and gradually modify it to achieve better super-resolution performance with reduced parameters. The specific approaches include: (1) increasing the receptive field of the attention branch, (2) replacing large dense convolution kernels with depth-wise separable convolutions, and (3) introducing pixel normalization. These approaches paint a clear evolutionary roadmap for the design of attention mechanisms. Based on these observations, we propose VapSR, the VAst-receptive-field Pixel attention network. Experiments demonstrate the superior performance of VapSR. VapSR outperforms the present lightweight networks with even fewer parameters. And the light version of VapSR can use only 21.68% and 28.18% parameters of IMDB and RFDN to achieve similar performances to those networks. The code and models are available at https://github.com/zhoumumu/VapSR.

eess.IV↗

arXiv2022

Rethinking Alignment in Video Super-Resolution Transformers

The alignment of adjacent frames is considered an essential operation in video super-resolution (VSR). Advanced VSR models, including the latest VSR Transformers, are generally equipped with well-designed alignment modules. However, the progress of the self-attention mechanism may violate this common sense. In this paper, we rethink the role of alignment in VSR Transformers and make several counter-intuitive observations. Our experiments show that: (i) VSR Transformers can directly utilize multi-frame information from unaligned videos, and (ii) existing alignment methods are sometimes harmful to VSR Transformers. These observations indicate that we can further improve the performance of VSR Transformers simply by removing the alignment module and adopting a larger attention window. Nevertheless, such designs will dramatically increase the computational burden, and cannot deal with large motions. Therefore, we propose a new and efficient alignment method called patch alignment, which aligns image patches instead of pixels. VSR Transformers equipped with patch alignment could demonstrate state-of-the-art performance on multiple benchmarks. Our work provides valuable insights on how multi-frame information is used in VSR and how to select alignment methods for different networks/datasets. Codes and models will be released at https://github.com/XPixelGroup/RethinkVSRAlignment.

cs.CV↗

arXiv2022

A Survey on the Network Models applied in the Industrial Network Optimization

Network architecture design is very important for the optimization of industrial networks. The type of network architecture can be divided into small-scale network and large-scale network according to its scale. Graph theory is an efficient mathematical tool for network topology modeling. For small-scale networks, its structure often has regular topology. For large-scale networks, the existing research mainly focuses on the random characteristics of network nodes and edges. Recently, popular models include random networks, small-world networks and scale-free networks. Starting from the scale of network, this survey summarizes and analyzes the network modeling methods based on graph theory and the practical application in industrial scenarios. Furthermore, this survey proposes a novel network performance metric - system entropy. From the perspective of mathematical properties, the analysis of its non-negativity, monotonicity and concave-convexity is given. The advantage of system entropy is that it can cover the existing regular network, random network, small-world network and scale-free network, and has strong generality. The simulation results show that this metric can realize the comparison of various industrial networks under different models.

cs.SI↗

arXiv2022

UDC-UNet: Under-Display Camera Image Restoration via U-Shape Dynamic Network

Under-Display Camera (UDC) has been widely exploited to help smartphones realize full screen display. However, as the screen could inevitably affect the light propagation process, the images captured by the UDC system usually contain flare, haze, blur, and noise. Particularly, flare and blur in UDC images could severely deteriorate the user experience in high dynamic range (HDR) scenes. In this paper, we propose a new deep model, namely UDC-UNet, to address the UDC image restoration problem with the known Point Spread Function (PSF) in HDR scenes. On the premise that Point Spread Function (PSF) of the UDC system is known, we treat UDC image restoration as a non-blind image restoration problem and propose a novel learning-based approach. Our network consists of three parts, including a U-shape base network to utilize multi-scale information, a condition branch to perform spatially variant modulation, and a kernel branch to provide the prior knowledge of the given PSF. According to the characteristics of HDR data, we additionally design a tone mapping loss to stabilize network optimization and achieve better visual quality. Experimental results show that the proposed UDC-UNet outperforms the state-of-the-art methods in quantitative and qualitative comparisons. Our approach won the second place in the UDC image restoration track of MIPI challenge. Codes will be publicly available.

eess.IV↗

arXiv2022

Recurrent LSTM-based UAV Trajectory Prediction with ADS-B Information

Recently, unmanned aerial vehicles (UAVs) are gathering increasing attentions from both the academia and industry. The ever-growing number of UAV brings challenges for air traffic control (ATC), and thus trajectory prediction plays a vital role in ATC, especially for avoiding collisions among UAVs. However, the dynamic flight of UAV aggravates the complexity of trajectory prediction. Different with civil aviation aircrafts, the most intractable difficulty for UAV trajectory prediction depends on acquiring effective location information. Fortunately, the automatic dependent surveillance-broadcast (ADS-B) is an effective technique to help obtain positioning information. It is widely used in the civil aviation aircraft, due to its high data update frequency and low cost of corresponding ground stations construction. Hence, in this work, we consider leveraging ADS-B to help UAV trajectory prediction. However, with the ADS-B information for a UAV, it still lacks efficient mechanism to predict the UAV trajectory. It is noted that the recurrent neural network (RNN) is available for the UAV trajectory prediction, in which the long short-term memory (LSTM) is specialized in dealing with the time-series data. As above, in this work, we design a system of UAV trajectory prediction with the ADS-B information, and propose the recurrent LSTM (RLSTM) based algorithm to achieve the accurate prediction. Finally, extensive simulations are conducted by Python to evaluate the proposed algorithms, and the results show that the average trajectory prediction error is satisfied, which is in line with expectations.

eess.SP↗

arXiv2022

PS-NeRV: Patch-wise Stylized Neural Representations for Videos

We study how to represent a video with implicit neural representations (INRs). Classical INRs methods generally utilize MLPs to map input coordinates to output pixels. While some recent works have tried to directly reconstruct the whole image with CNNs. However, we argue that both the above pixel-wise and image-wise strategies are not favorable to video data. Instead, we propose a patch-wise solution, PS-NeRV, which represents videos as a function of patches and the corresponding patch coordinate. It naturally inherits the advantages of image-wise methods, and achieves excellent reconstruction performance with fast decoding speed. The whole method includes conventional modules, like positional embedding, MLPs and CNNs, while also introduces AdaIN to enhance intermediate features. These simple yet essential changes could help the network easily fit high-frequency details. Extensive experiments have demonstrated its effectiveness in several video-related tasks, such as video compression and video inpainting.

cs.CV↗

arXiv2022

Phase diagrams on composition-spread Fe$_y$Te$_{1-x}$Se$_x$ films

Fe$_y$Te$_{1-x}$Se$_x$, an archetypical iron-based high-temperature superconductor with a simple structure but rich physical properties, has attracted lots of attention because the two end compositions, Se content $x = 0$ and 1, exhibit antiferromagnetism and nematicity, respectively, making it an ideal candidate for studying their interactions with superconductivity. However, what is clearly lacking to date is a complete phase diagram of Fe$_y$Te$_{1-x}$Se$_x$ as functions of its chemical compositions since phase separation usually occurs from $x\sim 0.6$ to 0.9 in bulk crystals. Moreover, fine control of its composition is experimentally challenging because both Te and Se are volatile elements. Here we establish a complete phase diagram of Fe$_y$Te$_{1-x}$Se$_x$, achieved by high-throughput film synthesis and characterization techniques. An advanced combinatorial synthesis process enables us to fabricate an epitaxial composition-spread Fe$_y$Te$_{1-x}$Se$_x$ film encompassing the entire Se content $x$ from 0 to 1 on a single piece of CaF$_2$ substrate. The micro-region composition analysis and X-ray diffraction show a successful continuous tuning of chemical compositions and lattice parameters, respectively. The micro-scale pattern technique allows the mapping of electrical transport properties as a function of relative Se content with an unprecedented resolution of 0.0074. Combining with the spin patterns in literature, we build a detailed phase diagram that can unify the electronic and magnetic properties of Fe$_y$Te$_{1-x}$Se$_x$. Our composition-spread Fe$_y$Te$_{1-x}$Se$_x$ films, overcoming the challenges of phase separation and precise control of chemical compositions, provide an ideal platform for studying the relationship between superconductivity and magnetism.

cond-mat.supr-con↗

arXiv2022

MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolution

Interactive image restoration aims to restore images by adjusting several controlling coefficients, which determine the restoration strength. Existing methods are restricted in learning the controllable functions under the supervision of known degradation types and levels. They usually suffer from a severe performance drop when the real degradation is different from their assumptions. Such a limitation is due to the complexity of real-world degradations, which can not provide explicit supervision to the interactive modulation during training. However, how to realize the interactive modulation in real-world super-resolution has not yet been studied. In this work, we present a Metric Learning based Interactive Modulation for Real-World Super-Resolution (MM-RealSR). Specifically, we propose an unsupervised degradation estimation strategy to estimate the degradation level in real-world scenarios. Instead of using known degradation levels as explicit supervision to the interactive mechanism, we propose a metric learning strategy to map the unquantifiable degradation levels in real-world scenarios to a metric space, which is trained in an unsupervised manner. Moreover, we introduce an anchor point strategy in the metric learning process to normalize the distribution of metric space. Extensive experiments demonstrate that the proposed MM-RealSR achieves excellent modulation and restoration performance in real-world super-resolution. Codes are available at https://github.com/TencentARC/MM-RealSR.

cs.CV↗

arXiv2022

VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

Although generative facial prior and geometric prior have recently demonstrated high-quality results for blind face restoration, producing fine-grained facial details faithful to inputs remains a challenging problem. Motivated by the classical dictionary-based methods and the recent vector quantization (VQ) technique, we propose a VQ-based face restoration method - VQFR. VQFR takes advantage of high-quality low-level feature banks extracted from high-quality faces and can thus help recover realistic facial details. However, the simple application of the VQ codebook cannot achieve good results with faithful details and identity preservation. Therefore, we further introduce two special network designs. 1). We first investigate the compression patch size in the VQ codebook and find that the VQ codebook designed with a proper compression patch size is crucial to balance the quality and fidelity. 2). To further fuse low-level features from inputs while not "contaminating" the realistic details generated from the VQ codebook, we proposed a parallel decoder consisting of a texture decoder and a main decoder. Those two decoders then interact with a texture warping module with deformable convolution. Equipped with the VQ codebook as a facial detail dictionary and the parallel decoder design, the proposed VQFR can largely enhance the restored quality of facial details while keeping the fidelity to previous methods.

cs.CV↗

arXiv2022

Semantic-Sparse Colorization Network for Deep Exemplar-based Colorization

Exemplar-based colorization approaches rely on reference image to provide plausible colors for target gray-scale image. The key and difficulty of exemplar-based colorization is to establish an accurate correspondence between these two images. Previous approaches have attempted to construct such a correspondence but are faced with two obstacles. First, using luminance channels for the calculation of correspondence is inaccurate. Second, the dense correspondence they built introduces wrong matching results and increases the computation burden. To address these two problems, we propose Semantic-Sparse Colorization Network (SSCN) to transfer both the global image style and detailed semantic-related colors to the gray-scale image in a coarse-to-fine manner. Our network can perfectly balance the global and local colors while alleviating the ambiguous matching problem. Experiments show that our method outperforms existing methods in both quantitative and qualitative evaluation and achieves state-of-the-art performance.

cs.CV↗