arXiv subjects

Xin Tao

Publications and source records attributed to Xin Tao.

At least 91 records · Page 5Linked to original sources

arXiv2022

Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling

Temporal modeling is crucial for video super-resolution. Most of the video super-resolution methods adopt the optical flow or deformable convolution for explicitly motion compensation. However, such temporal modeling techniques increase the model complexity and might fail in case of occlusion or complex motion, resulting in serious distortion and artifacts. In this paper, we propose to explore the role of explicit temporal difference modeling in both LR and HR space. Instead of directly feeding consecutive frames into a VSR model, we propose to compute the temporal difference between frames and divide those pixels into two subsets according to the level of difference. They are separately processed with two branches of different receptive fields in order to better extract complementary information. To further enhance the super-resolution result, not only spatial residual features are extracted, but the difference between consecutive frames in high-frequency domain is also computed. It allows the model to exploit intermediate SR results in both future and past to refine the current SR output. The difference at different time steps could be cached such that information from further distance in time could be propagated to the current frame for refinement. Experiments on several video super-resolution benchmark datasets demonstrate the effectiveness of the proposed method and its favorable performance against state-of-the-art methods.

cs.CV↗

arXiv2022

Real-time decision-making for autonomous vehicles under faults

This paper addresses the challenges of decision-making for autonomous vehicles under faults during a transport mission. A real-time decision-making problem of vehicle routing planning considering maintenance management is formulated as an optimization problem. The goal is to minimize the total time to finish the transport mission by selecting the optimal workshop to conduct the maintenance and the corresponding routes. Two methods are proposed to solve the optimization problem based on two methods of fundamental solutions: (1) Mixed Integer Programming; (2) Dijkstra's algorithm. We adapt these methods to solve the optimization problem and consider improving the computation efficiency. Numerical studies of test cases of highway and urban scenarios are presented to demonstrate the proposed methods, which show the feasibility and high computational efficiency of both methods.

eess.SY↗

arXiv2021

Finding Critical Scenarios for Automated Driving Systems: A Systematic Literature Review

Scenario-based approaches have been receiving a huge amount of attention in research and engineering of automated driving systems. Due to the complexity and uncertainty of the driving environment, and the complexity of the driving task itself, the number of possible driving scenarios that an ADS or ADAS may encounter is virtually infinite. Therefore it is essential to be able to reason about the identification of scenarios and in particular critical ones that may impose unacceptable risk if not considered. Critical scenarios are particularly important to support design, verification and validation efforts, and as a basis for a safety case. In this paper, we present the results of a systematic literature review in the context of autonomous driving. The main contributions are: (i) introducing a comprehensive taxonomy for critical scenario identification methods; (ii) giving an overview of the state-of-the-art research based on the taxonomy encompassing 86 papers between 2017 and 2020; and (iii) identifying open issues and directions for further research. The provided taxonomy comprises three main perspectives encompassing the problem definition (the why), the solution (the methods to derive scenarios), and the assessment of the established scenarios. In addition, we discuss open research issues considering the perspectives of coverage, practicability, and scenario space explosion.

cs.SE↗

arXiv2021

Nonlinear dynamics and phase space transport by chorus emission

Chorus emission in planetary magnetospheres is taken as working paradigm to motivate a short tutorial trip through theoretical plasma physics methods and their applications. Starting from basic linear theory, readers are first made comfortable with whistler wave packets and their propagation in slowly varying weakly nonuniform media, such as the Earth's magnetosphere, where they can be amplified by a population of supra-thermal electrons. The nonlinear dynamic description of energetic electrons in the phase space in the presence of self-consistently evolving whistler fluctuation spectrum is progressively introduced by addressing renormalization of the electron response and spectrum evolution equations. Analytical and numerical results on chorus frequency chirping are obtained and compared with existing observations and particle in cell simulations. Finally, the general theoretical framework constructed during this short trip through chorus physics is used to draw analogies with condensed matter and laser physics as well as magnetic confinement fusion research. Discussing these analogies ultimately presents plasma physics as an exciting cross-disciplinary field to study.

physics.plasm-ph↗

arXiv2021

MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution

Reference-based image super-resolution (RefSR) has shown promising success in recovering high-frequency details by utilizing an external reference image (Ref). In this task, texture details are transferred from the Ref image to the low-resolution (LR) image according to their point- or patch-wise correspondence. Therefore, high-quality correspondence matching is critical. It is also desired to be computationally efficient. Besides, existing RefSR methods tend to ignore the potential large disparity in distributions between the LR and Ref images, which hurts the effectiveness of the information utilization. In this paper, we propose the MASA network for RefSR, where two novel modules are designed to address these problems. The proposed Match & Extraction Module significantly reduces the computational cost by a coarse-to-fine correspondence matching scheme. The Spatial Adaptation Module learns the difference of distribution between the LR and Ref images, and remaps the distribution of Ref features to that of LR features in a spatially adaptive way. This scheme makes the network robust to handle different reference images. Extensive quantitative and qualitative experiments validate the effectiveness of our proposed model.

cs.CV↗

arXiv2021

Short-term Maintenance Planning of Autonomous Trucks for Minimizing Economic Risk

New autonomous driving technologies are emerging every day and some of them have been commercially applied in the real world. While benefiting from these technologies, autonomous trucks are facing new challenges in short-term maintenance planning, which directly influences the truck operator's profit. In this paper, we implement a vehicle health management system by addressing the maintenance planning issues of autonomous trucks on a transport mission. We also present a maintenance planning model using a risk-based decision-making method, which identifies the maintenance decision with minimal economic risk of the truck company. Both availability losses and maintenance costs are considered when evaluating the economic risk. We demonstrate the proposed model by numerical experiments illustrating real-world scenarios. In the experiments, compared to three baseline methods, the expected economic risk of the proposed method is reduced by up to $47\%$. We also conduct sensitivity analyses of different model parameters. The analyses show that the economic risk significantly decreases when the estimation accuracy of remaining useful life, the maximal allowed time of delivery delay before order cancellation, or the number of workshops increases. The experiment results contribute to identifying future research and development attentions of autonomous trucks from an economic perspective.

cs.AI↗

arXiv2021

A "Trap-Release-Amplify" Model of Chorus Waves

Whistler mode chorus waves are quasi-coherent electromagnetic emissions with frequency chirping. Various models have been proposed to understand the chirping mechanism, which is a long-standing problem in space plasmas. Based on analysis of effective wave growth rate and electron phase space dynamics in a self-consistent particle simulation, we propose here a phenomenological model called the "Trap-Release-Amplify" (TaRA) model for chorus. In this model, phase space structures of correlated electrons are formed by nonlinear wave particle interactions, which mainly occur in the downstream. When released from the wave packet in the upstream, these electrons selectively amplify new emissions which satisfy the phase-locking condition to maximize wave power transfer, leading to frequency chirping. The phase-locking condition at the release point gives a frequency chirping rate that is fully consistent with the one by Helliwell in case of a nonuniform background magnetic field. The nonlinear wave particle interaction part of the TaRA model results in a chirping rate that is proportional to wave amplitude, a conclusion originally reached by Vomvoridis et al. Therefore, the TaRA model unifies two different results from seemingly unrelated studies. Furthermore, the TaRA model naturally explains fine structures of chorus waves, including subpackets and bandwidth, and their evolution through dynamics of phase-trapped electrons. Finally, we suggest that this model could be applied to explain other related phenomena, including frequency chirping of chorus in a uniform background magnetic field and of electromagnetic ion cyclotron waves in the magnetosphere.

physics.plasm-ph↗

arXiv2020

MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution

Video super-resolution (VSR) aims to utilize multiple low-resolution frames to generate a high-resolution prediction for each frame. In this process, inter- and intra-frames are the key sources for exploiting temporal and spatial information. However, there are a couple of limitations for existing VSR methods. First, optical flow is often used to establish temporal correspondence. But flow estimation itself is error-prone and affects recovery results. Second, similar patterns existing in natural images are rarely exploited for the VSR task. Motivated by these findings, we propose a temporal multi-correspondence aggregation strategy to leverage similar patches across frames, and a cross-scale nonlocal-correspondence aggregation scheme to explore self-similarity of images across scales. Based on these two new modules, we build an effective multi-correspondence aggregation network (MuCAN) for VSR. Our method achieves state-of-the-art results on multiple benchmark datasets. Extensive experiments justify the effectiveness of our method.

cs.CV↗

arXiv2020

VCNet: A Robust Approach to Blind Image Inpainting

Blind inpainting is a task to automatically complete visual contents without specifying masks for missing areas in an image. Previous works assume missing region patterns are known, limiting its application scope. In this paper, we relax the assumption by defining a new blind inpainting setting, making training a blind inpainting neural system robust against various unknown missing region patterns. Specifically, we propose a two-stage visual consistency network (VCN), meant to estimate where to fill (via masks) and generate what to fill. In this procedure, the unavoidable potential mask prediction errors lead to severe artifacts in the subsequent repairing. To address it, our VCN predicts semantically inconsistent regions first, making mask prediction more tractable. Then it repairs these estimated missing regions using a new spatial normalization, enabling VCN to be robust to the mask prediction errors. In this way, semantically convincing and visually compelling content is thus generated. Extensive experiments are conducted, showing our method is effective and robust in blind image inpainting. And our VCN allows for a wide spectrum of applications.

cs.CV↗

arXiv2020

Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisons

Conditional generative adversarial networks have shown exceptional generation performance over the past few years. However, they require large numbers of annotations. To address this problem, we propose a novel generative adversarial network utilizing weak supervision in the form of pairwise comparisons (PC-GAN) for image attribute editing. In the light of Bayesian uncertainty estimation and noise-tolerant adversarial training, PC-GAN can estimate attribute rating efficiently and demonstrate robust performance in noise resistance. Through extensive experiments, we show both qualitatively and quantitatively that PC-GAN performs comparably with fully-supervised methods and outperforms unsupervised baselines.

cs.LG↗

arXiv2019

Architecting Safety Supervisors for High Levels of Automated Driving

The complexity of automated driving poses challenges for providing safety assurance. Focusing on the architecting of an Autonomous Driving Intelligence (ADI), i.e. the computational intelligence, sensors and communication needed for high levels of automated driving, we investigate so called safety supervisors that complement the nominal functionality. We present a problem formulation and a functional architecture of a fault-tolerant ADI that encompasses a nominal and a safety supervisor channel. We then discuss the sources of hazardous events, the division of responsibilities among the channels, and when the supervisor should take over. We conclude with identified directions for further work.

eess.SY↗

arXiv2019

Attribute-Driven Spontaneous Motion in Unpaired Image Translation

Current image translation methods, albeit effective to produce high-quality results in various applications, still do not consider much geometric transform. We in this paper propose the spontaneous motion estimation module, along with a refinement part, to learn attribute-driven deformation between source and target domains. Extensive experiments and visualization demonstrate effectiveness of these modules. We achieve promising results in unpaired-image translation tasks, and enable interesting applications based on spontaneous motion.

cs.CV↗

arXiv2019

Landmark Assisted CycleGAN for Cartoon Face Generation

In this paper, we are interested in generating an cartoon face of a person by using unpaired training data between real faces and cartoon ones. A major challenge of this task is that the structures of real and cartoon faces are in two different domains, whose appearance differs greatly from each other. Without explicit correspondence, it is difficult to generate a high quality cartoon face that captures the essential facial features of a person. In order to solve this problem, we propose landmark assisted CycleGAN, which utilizes face landmarks to define landmark consistency loss and to guide the training of local discriminator in CycleGAN. To enforce structural consistency in landmarks, we utilize the conditional generator and discriminator. Our approach is capable to generate high-quality cartoon faces even indistinguishable from those drawn by artists and largely improves state-of-the-art.

cs.CV↗

arXiv2018

Image Inpainting via Generative Multi-column Convolutional Neural Networks

In this paper, we propose a generative multi-column network for image inpainting. This network synthesizes different image components in a parallel manner within one stage. To better characterize global structures, we design a confidence-driven reconstruction loss while an implicit diversified MRF regularization is adopted to enhance local details. The multi-column network combined with the reconstruction and MRF loss propagates local and global information derived from context to the target inpainting regions. Extensive experiments on challenging street view, face, natural objects and scenes manifest that our method produces visual compelling results even without previously common post-processing.

cs.CV↗

arXiv2018

Facelet-Bank for Fast Portrait Manipulation

Digital face manipulation has become a popular and fascinating way to touch images with the prevalence of smartphones and social networks. With a wide variety of user preferences, facial expressions, and accessories, a general and flexible model is necessary to accommodate different types of facial editing. In this paper, we propose a model to achieve this goal based on an end-to-end convolutional neural network that supports fast inference, edit-effect control, and quick partial-model update. In addition, this model learns from unpaired image sets with different attributes. Experimental results show that our framework can handle a wide range of expressions, accessories, and makeup effects. It produces high-resolution and high-quality results in fast speed.

cs.CV↗

arXiv2018

Scale-recurrent Network for Deep Image Deblurring

In single image deblurring, the "coarse-to-fine" scheme, i.e. gradually restoring the sharp image on different resolutions in a pyramid, is very successful in both traditional optimization-based methods and recent neural-network-based approaches. In this paper, we investigate this strategy and propose a Scale-recurrent Network (SRN-DeblurNet) for this deblurring task. Compared with the many recent learning-based approaches in [25], it has a simpler network structure, a smaller number of parameters and is easier to train. We evaluate our method on large-scale deblurring datasets with complex motion. Results show that our method can produce better quality results than state-of-the-arts, both quantitatively and qualitatively.

cs.CV↗

arXiv2017

Zero-order Reverse Filtering

In this paper, we study an unconventional but practically meaningful reversibility problem of commonly used image filters. We broadly define filters as operations to smooth images or to produce layers via global or local algorithms. And we raise the intriguingly problem if they are reservable to the status before filtering. To answer it, we present a novel strategy to understand general filter via contraction mappings on a metric space. A very simple yet effective zero-order algorithm is proposed. It is able to practically reverse most filters with low computational cost. We present quite a few experiments in the paper and supplementary file to thoroughly verify its performance. This method can also be generalized to solve other inverse problems and enables new applications.

cs.CV↗

arXiv2017

Detail-revealing Deep Video Super-resolution

Previous CNN-based video super-resolution approaches need to align multiple frames to the reference. In this paper, we show that proper frame alignment and motion compensation is crucial for achieving high quality results. We accordingly propose a `sub-pixel motion compensation' (SPMC) layer in a CNN framework. Analysis and experiments show the suitability of this layer in video SR. The final end-to-end, scalable CNN framework effectively incorporates the SPMC layer and fuses multiple frames to reveal image details. Our implementation can generate visually and quantitatively high-quality results, superior to current state-of-the-arts, without the need of parameter tuning.

cs.CV↗