5 papers
EF-VI: Enhancing End-Frame Injection for Video Inbetweening
Liuhan Chen, Xiaodong Cun, Xiaoyu Li +5
Video inbetweening aims to synthesize intermediate video sequences conditioned on the given start and end frames. Current state-of-the-art methods primarily extend large-scale pre-…
Next Patch Prediction for Autoregressive Visual Generation
Yatian Pang, Peng Jin, Shuo Yang +8
Autoregressive models, built based on the Next Token Prediction (NTP) paradigm, show great potential in developing a unified framework that integrates both language and vision task…
WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model
Zongjian Li, Bin Lin, Yang Ye +4
Video Variational Autoencoder (VAE) encodes videos into a low-dimensional latent space, becoming a key component of most Latent Video Diffusion Models (LVDMs) to reduce model train…
Identity-Preserving Text-to-Video Generation by Frequency Decomposition
Shenghai Yuan, Jinfa Huang, Xianyi He +5
Identity-preserving text-to-video (IPT2V) generation aims to create high-fidelity videos with consistent human identity. It is an important task in video generation but remains an…
OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model
Liuhan Chen, Zongjian Li, Bin Lin +6
Variational Autoencoder (VAE), compressing videos into latent representations, is a crucial preceding component of Latent Video Diffusion Models (LVDMs). With the same reconstructi…