Search

Human image animation involves generating a video from a static image by following a specified pose sequence. Current approaches typically adopt a multi-stage pipeline that separately learns appearance and motion, which often leads to appearance degradation and temporal inconsistencies. To address these issues, we propose VividPose, an innovative end-to-end pipeline based on Stable Video Diffusion (SVD) that ensures superior temporal stability. To enhance the retention of human identity, we propose an identity-aware appearance controller that integrates additional facial information without compromising other appearance details such as clothing texture and background. This approach ensures that the generated videos maintain high fidelity to the identity of human subject, preserving key facial features across various poses. To accommodate diverse human body shapes and hand movements, we introduce a geometry-aware pose controller that utilizes both dense rendering maps from SMPL-X and sparse skeleton maps. This enables accurate alignment of pose and shape in the generated videos, providing a robust framework capable of handling a wide range of body shapes and dynamic hand movements. Extensive qualitative and quantitative experiments on the UBCFashion and TikTok benchmarks demonstrate that our method achieves state-of-the-art performance. Furthermore, VividPose exhibits superior generalization capabilities on our proposed in-the-wild dataset. Codes and models will be available.

Facial Appearance Editing (FAE) aims to modify physical attributes, such as pose, expression and lighting, of human facial images while preserving attributes like identity and background, showing great importance in photograph. In spite of the great progress in this area, current researches generally meet three challenges: low generation fidelity, poor attribute preservation, and inefficient inference. To overcome above challenges, this paper presents DiffFAE, a one-stage and highly-efficient diffusion-based framework tailored for high-fidelity FAE. For high-fidelity query attributes transfer, we adopt Space-sensitive Physical Customization (SPC), which ensures the fidelity and generalization ability by utilizing rendering texture derived from 3D Morphable Model (3DMM). In order to preserve source attributes, we introduce the Region-responsive Semantic Composition (RSC). This module is guided to learn decoupled source-regarding features, thereby better preserving the identity and alleviating artifacts from non-facial attributes such as hair, clothes, and background. We further introduce a consistency regularization for our pipeline to enhance editing controllability by leveraging prior knowledge in the attention matrices of diffusion model. Extensive experiments demonstrate the superiority of DiffFAE over existing methods, achieving state-of-the-art performance in facial appearance editing.

In this work, we study a coupled system of two V-type atoms with dipole-dipole interaction in a dissipative single-mode cavity, which couples with an external environment. We obtain the analytical solution of this model by solving the time dependent Schrodinger equation after we diagonalize Hamiltonian of dissipative cavity by introducing a set of new creation and annihilation operators according to Fano theorem. We also detailedly discuss the influences of cavity-environment coupling, spontaneously generated interference (SGI) parameter and dipole-dipole interaction between two atoms on entanglement dynamics under different initial states. The results show that the SGI parameter has different effects on entanglement dynamics under different initial states. Namely, the SGI parameter will increase the decay rate of the initially maximal entangled state and reduce that of the initially partial entangled state. For the initially product state, the larger SGI parameter corresponds to the more entanglement generated. The entanglement monotonically decreases under the weak cavity-environment coupling, while the oscillation of entanglement will occur under the strong cavity-environment coupling. The larger the dipole-dipole interaction is, the slower the entanglement decays and the more the entanglement will be generated. So the dipole-dipole interaction can not only protect and generate entanglement very effectively, but also enhance the regulation effect of the SGI parameter on entanglement., Comment: 12 pages, 9 figures

In this work, we study quantum evolution of an open moving-qubit modulated by a classical driving field. We obtain the density operator of qubit at zero temperature and analyze its quantum evolution dynamics by using quantum speed limit time (QSLT) and a non-Markovianity measure introduced recently. The results show that both the non-Markovian environment and the classical driving can speed up the evolution process, this quantum speedup process is induced by the non-Markovianity and the critical points only depend on the qubit velocity. Moreover, the qubit motion will delay the evolution process, but this negative effect of the qubit velocity on the quantum speedup can be suppressed by the classical driving. Finally, we give the corresponding physical explanation by using the decoherence rates., Comment: 10 pages, 12figures

In this work, the entanglement dynamics of a moving-biparticle system driven by an external classical field are investigated, where the moving-biparticle system is coupled with a zero temperature common environment. The analytical expressions of the density operator and the entanglement can be obtained by using the dressed-state basis when the total excitation number is one. We also discuss in detail the effects of different parameters on the entanglement dynamics. The results show that the classical driving can not only protect the entanglement, but also effectively eliminate the influence of the qubit velocity and the detuning on the quantum entanglement., Comment: 8 pages, 11 figures