Temporal Regularization Makes Your Video Generator Stronger
Temporal quality is a critical aspect of video generation, as it ensures consistent motion and realistic dynamics across frames. However, achieving high temporal coherence and diversity remains challenging. In this work, we explore temporal augmentation in video generation for the first time, and introduce FluxFlow for initial investigation, a strategy designed to enhance temporal quality. Operating at the data level, FluxFlow applies controlled temporal perturbations without requiring architectural modifications. Extensive experiments on UCF-101 and VBench benchmarks demonstrate that FluxFlow significantly improves temporal coherence and diversity across various video generation models, including U-Net, DiT, and AR-based architectures, while preserving spatial fidelity. These findings highlight the potential of temporal augmentation as a simple yet effective approach to advancing video generation quality.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityVideo GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Intrinsic Temporal Regularization for High-resolution Human Video Synthesis
Temporal consistency is crucial for extending image processing pipelines to the video domain, which is often enforced with flow-based warping error over adjacent frames. Yet for human video synthesis, such scheme is less…
Motion EstimationVocal Bursts Intensity PredictionFollow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation
This paper explores higher-resolution video outpainting with extensive content generation. We point out common issues faced by existing methods when attempting to largely outpaint videos: the generation of low-quality co…
GPUAlign your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to…
Image GenerationSuper-ResolutionText-to-Video GenerationVideo Generation+2Detecting AI-Generated Videos with Spiking Neural Networks
Modern AI-generated videos are photorealistic at the single-frame level, leaving inter-frame dynamics as the main remaining axis for detection. Existing detectors typically handle this temporal evidence in three ways: fe…
Dance Your Latents: Consistent Dance Generation through Spatial-temporal Subspace Attention Guided by Motion Flow
The advancement of generative AI has extended to the realm of Human Dance Generation, demonstrating superior generative capacities. However, current methods still exhibit deficiencies in achieving spatiotemporal consiste…