paper-with-me

홈 › Papers

VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption

2025-05-17 · Tianxiong Zhong, Xingye Tian, Boyuan Jiang, Xuebo Wang, Xin Tao, Pengfei Wan, Zhiwei Zhang

Modern video generation frameworks based on Latent Diffusion Models suffer from inefficiencies in tokenization due to the Frame-Proportional Information Assumption. Existing tokenizers provide fixed temporal compression rates, causing the computational cost of the diffusion model to scale linearly with the frame rate. The paper proposes the Duration-Proportional Information Assumption: the upper bound on the information capacity of a video is proportional to the duration rather than the number of frames. Based on this insight, the paper introduces VFRTok, a Transformer-based video tokenizer, that enables variable frame rate encoding and decoding through asymmetric frame rate training between the encoder and decoder. Furthermore, the paper proposes Partial Rotary Position Embeddings (RoPE) to decouple position and content modeling, which groups correlated patches into unified tokens. The Partial RoPE effectively improves content-awareness, enhancing the video generation capability. Benefiting from the compact and continuous spatio-temporal representation, VFRTok achieves competitive reconstruction quality and state-of-the-art generation fidelity while using only 1/8 tokens compared to existing tokenizers.

📄 PDF Abstract BibTeX arXiv:2505.12053

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderPositionVideo Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression

2025-12-18 · Haotian Ye, Qiyuan He, Jiaqi Han, Puheng Li 외 arxiv

Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottleneck for current to…

OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation

2024-06-13 · Junke Wang, Yi Jiang, Zehuan Yuan, Binyue Peng 외

Tokenizer, serving as a translator to map the intricate visual data into a compact latent space, lies at the core of visual generative models. Based on the finding that existing tokenizers are tailored to image or video …

Video GenerationVideo Prediction

VidTok: A Versatile and Open-Source Video Tokenizer

2024-12-17 · Anni Tang, Tianyu He, Junliang Guo, Xinle Cheng 외

Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations. Consequently, t…

QuantizationSSIMVideo Generation

VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization

2026-04-14 · Andrei Atanov, Jesse Allardice, Roman Bachmann, Oğuzhan Fatih Kar 외 arxiv

Visual tokenizers map high-dimensional raw pixels into a compressed representation for downstream modeling. Beyond compression, tokenizers dictate what information is preserved and how it is organized. A de facto standar…

Video Generation

EO-VAE: Towards A Multi-sensor Tokenizer for Earth Observation Data

2026-02-12 · Nils Lehmann, Yi Wang, Zhitong Xiong, Xiaoxiang Zhu arxiv

State-of-the-art generative image and video models rely heavily on tokenizers that compress high-dimensional inputs into more efficient latent representations. While this paradigm has revolutionized RGB generation, Earth…