Temporally consistent video colorization with deep feature propagation and self-regularization learning

Video colorization is a challenging and highly ill-posed problem.Although recent years have witnessed remarkable progress in single image colorization,there is relatively less research effort on video colorization,and existing methods always suffer from severe flickering artifacts(temporal inconsistency)or unsatisfactory colorization.We address this problem from a new perspective,by jointly considering colorization and temporal consistency in a unified framework.Specifically,we propose a novel temporally consistent video colorization(TCVC)framework.TCVC effectively propagates frame-level deep features in a bidirectional way to enhance the temporal consistency of colorization.Furthermore,TCVC introduces a self-regularization learning(SRL)scheme to minimize the differences in predictions obtained using different time steps.SRL does not require any ground-truth color videos for training and can further improve temporal consistency.Experiments demonstrate that our method can not only provide visually pleasing colorized video,but also with clearly better temporal consistency than state-of-the-art methods.A video demo is provided at https://www.youtube.com/watch?v=c7dczMs-olE,while code is available at https://github.com/lyh-18/TCVC-Tem porally-Consistent-Video-Colorization.

A Modified Formulation of Singular Boundary Method for Exterior Acoustics

This paper proposes amodified formulation of the singular boundarymethod(SBM)by introducing the combined Helmholtz integral equation formulation(CHIEF)and the self-regularization technique to exterior acoustics.In the SBM,the concept of the origin intensity factor(OIF)is introduced to avoid the singularities of the fundamental solutions.The SBM belongs to the meshless boundary collocation methods.The additional use of the CHIEF scheme and the self-regularization technique in the SBM guarantees the unique solution of the exterior acoustics accurately and efficiently.Consequently,by using the SBM coupled with the CHIEF scheme and the self-regularization technique,the accuracy of the numerical solution can be improved,especially near the corresponding internal characteristic frequencies.Several numerical examples of two-dimensional and threedimensional benchmark examples about exterior acoustics are used to verify the effectiveness and accuracy of the proposed method.The proposed numerical results are compared with the analytical solutions and the solutions obtained by the other numerical methods.

A Class of New Large-Update Primal-Dual Interior-Point Algorithms for P＊（k） Nonlinear Complementarity Problems

In this paper we propose a class of new large-update primal-dual interior-point algorithms for P.（k） nonlinear complementarity problem （NCP）, which are based on a class of kernel functions investigated by Bai et al. in their recent work for linear optimization （LO）. The arguments for the algorithms are followed as Peng et al.＇s for P.（n） complementarity problem based on the self-regular functions [Peng, J., Roos, C., Terlaky, T.： Self-Regularity： A New Paradigm for Primal-Dual Interior- Point Algorithms, Princeton University Press, Princeton, 2002]. It is worth mentioning that since this class of kernel functions includes a class of non-self-regular functions as special case, so our algorithms are different from Peng et al.＇s and the corresponding analysis is simpler than theirs. The ultimate goal of the paper is to show that the algorithms based on these functions have favorable polynomial complexity.