3 citations · 7 across the 10 of their papers we have counts for
11 papers
TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization
Weiliang Chen, Yuanhui Huang, Xuebo Wang +1
Video tokenization is fundamental to scalable video generation, as the number of tokens directly determines the computational cost and the length of videos that can be modeled. Exi…
Diffusing in the Right Space: A Systematic Study of Latent Diffusability
Tianxiong Zhong, Xingye Tian, Xuebo Wang +2
Latent diffusion models leverage visual tokenizers to compress images into latent spaces for efficient generative modeling. However, better reconstruction quality of a tokenizer do…
KlingAvatar 2.0 Technical Report
Kling Team, Jialu Chen, Yikang Ding +25
Avatar video generation models have achieved remarkable progress in recent years. However, prior work exhibits limited efficiency in generating long-duration high-resolution videos…
Decoupling Complexity from Scale in Latent Diffusion Model
Tianxiong Zhong, Xingye Tian, Xuebo Wang +3
Existing latent diffusion models typically couple scale with content complexity, using more latent tokens to represent higher-resolution images or higher-frame rate videos. However…
Denoising Vision Transformer Autoencoder with Spectral Self-Regularization
Xunzhi Xiang, Xingye Tian, Guiyu Zhang +5
Variational autoencoders (VAEs) typically encode images into a compact latent space, reducing computational cost but introducing an optimization dilemma: a higher-dimensional laten…
VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption
Tianxiong Zhong, Xingye Tian, Boyuan Jiang +4
Modern video generation frameworks based on Latent Diffusion Models suffer from inefficiencies in tokenization due to the Frame-Proportional Information Assumption. Existing tokeni…
VIVID-10M: A Dataset and Baseline for Versatile and Interactive Video Local Editing
Jiahao Hu, Tianxiong Zhong, Xuebo Wang +5
Diffusion-based image editing models have made remarkable progress in recent years. However, achieving high-quality video editing remains a significant challenge. One major hurdle…
DVIS++: Improved Decoupled Framework for Universal Video Segmentation
Tao Zhang, Xingye Tian, Yikang Zhou +7
We present the \textbf{D}ecoupled \textbf{VI}deo \textbf{S}egmentation (DVIS) framework, a novel approach for the challenging task of universal video segmentation, including video…
1st Place Solution for the 5th LSVOS Challenge: Video Instance Segmentation
Tao Zhang, Xingye Tian, Yikang Zhou +7
Video instance segmentation is a challenging task that serves as the cornerstone of numerous downstream applications, including video editing and autonomous driving. In this report…
DVIS: Decoupled Video Instance Segmentation Framework
Tao Zhang, Xingye Tian, Yu Wu +4
Video instance segmentation (VIS) is a critical task with diverse applications, including autonomous driving and video editing. Existing methods often underperform on complex and l…
1st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation
Tao Zhang, Xingye Tian, Haoran Wei +6
Video panoptic segmentation is a challenging task that serves as the cornerstone of numerous downstream applications, including video editing and autonomous driving. We believe tha…