arXiv subjects

Wenzhuo Li

Publications and source records attributed to Wenzhuo Li.

4 recordsLinked to original sources

arXiv2026

MemCam: Memory-Augmented Camera Control for Consistent Video Generation

Interactive video generation has significant potential for scene simulation and video creation. However, existing methods often struggle with maintaining scene consistency during long video generation under dynamic camera control due to limited contextual information. To address this challenge, we propose MemCam, a memory-augmented interactive video generation approach that treats previously generated frames as external memory and leverages them as contextual conditioning to achieve controllable camera viewpoints with high scene consistency. To enable longer and more relevant context, we design a context compression module that encodes memory frames into compact representations and employs co-visibility-based selection to dynamically retrieve the most relevant historical frames, thereby reducing computational overhead while enriching contextual information. Experiments on interactive video generation tasks show that MemCam significantly outperforms existing baseline methods as well as open-source state-of-the-art approaches in terms of scene consistency, particularly in long video scenarios with large camera rotations.

cs.CV↗

arXiv2025

Unraveling UV Stability in Metal Halide Perovskites: From Degradation Mechanisms to Molecular Passivation

Understanding the mechanisms of UV-induced degradation is crucial for enhancing the UV stability of perovskite solar cells. The UV-driven structural dynamics of CH3NH3PbI3 (MAPbI3) are investigated using real-time TDDFT simulations, revealing that under the electron and hole excitation, the distortion of the inorganic framework (PbI) is primarily driven by the electron occupation of Pb-p and I-p antibonding states, whereas in the hole case, it is mainly governed by the direct cooling induced distortion. We also find that UV accelerates the rotation of MA+ molecules. Further, a BDO molecule is introduced as a passivant, which suppresses structural distortions and provides multi-phonon channels to dissipate carrier cooling energy. Experimental results confirm the UV-protective role of BDO, with suppressed PbI2 formation and improved device stability. These results clarify the mechanism of the UV-induced degradation in the MAPbI3 perovskite and further elucidate how passivation molecules enhance UV stability.

cond-mat.mtrl-sci↗

arXiv2024

An open-source, adaptive solver for particle-resolved simulations with both subcycling and non-subcycling methods

We present the IAMReX, an adaptive and parallel solver for particle-resolved simulations on the multi-level grid. The fluid equations are solved using a finite-volume scheme on the block-structured semi-staggered grids with both subcycling and non-subcycling methods. The particle-fluid interaction is resolved using the multidirect forcing immersed boundary method. The associated Lagrangian markers used to resolve fluid-particle interface only exist on the finest-level grid, which greatly reduces memory usage. The volume integrals are numerically calculated to capture the free motion of particles accurately, and the repulsive potential model is also included to account for the particle-particle collision. We demonstrate the versatility, accuracy, and efficiency of the present multi-level framework by simulating fluid-particle interaction problems with various types of kinematic constraints. The cluster of monodisperse particles case is presented at the end to show the capability of the current solver in handing with multiple particles. The source code and testing cases used in this work can be accessed at https://github.com/ruohai0925/IAMR/tree/development. Input scripts and raw postprocessing data are also available for reproducing all results.

physics.flu-dyn↗

arXiv2023

IDO-VFI: Identifying Dynamics via Optical Flow Guidance for Video Frame Interpolation with Events

Video frame interpolation aims to generate high-quality intermediate frames from boundary frames and increase frame rate. While existing linear, symmetric and nonlinear models are used to bridge the gap from the lack of inter-frame motion, they cannot reconstruct real motions. Event cameras, however, are ideal for capturing inter-frame dynamics with their extremely high temporal resolution. In this paper, we propose an event-and-frame-based video frame interpolation method named IDO-VFI that assigns varying amounts of computation for different sub-regions via optical flow guidance. The proposed method first estimates the optical flow based on frames and events, and then decides whether to further calculate the residual optical flow in those sub-regions via a Gumbel gating module according to the optical flow amplitude. Intermediate frames are eventually generated through a concise Transformer-based fusion network. Our proposed method maintains high-quality performance while reducing computation time and computational effort by 10% and 17% respectively on Vimeo90K datasets, compared with a unified process on the whole region. Moreover, our method outperforms state-of-the-art frame-only and frames-plus-events methods on multiple video frame interpolation benchmarks. Codes and models are available at https://github.com/shicy17/IDO-VFI.

cs.CV↗