OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation

• URL: http://arxiv.org/abs/2406.09399v1
• Date: Thu, 13 Jun 2024 17:59:26 GMT
• Title: OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
• Authors: Junke Wang, Yi Jiang, Zehuan Yuan, Binyue Peng, Zuxuan Wu, Yu-Gang Jiang,
• Abstract summary: Tokenizer serves as a translator to map the intricate visual data into a compact latent space. This paper presents OmniTokenizer, a transformer-based tokenizer for joint image and video tokenization.
• Score: 95.29102596532854
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 inputs, this paper presents OmniTokenizer, a transformer-based tokenizer for joint image and video tokenization. OmniTokenizer is designed with a spatial-temporal decoupled architecture, which integrates window and causal attention for spatial and temporal modeling. To exploit the complementary nature of image and video data, we further propose a progressive training strategy, where OmniTokenizer is first trained on image data on a fixed resolution to develop the spatial encoding capacity and then jointly trained on image and video data on multiple resolutions to learn the temporal dynamics. OmniTokenizer, for the first time, handles both image and video inputs within a unified framework and proves the possibility of realizing their synergy. Extensive experiments demonstrate that OmniTokenizer achieves state-of-the-art (SOTA) reconstruction performance on various image and video datasets, e.g., 1.11 reconstruction FID on ImageNet and 42 reconstruction FVD on UCF-101, beating the previous SOTA methods by 13% and 26%, respectively. Additionally, we also show that when integrated with OmniTokenizer, both language model-based approaches and diffusion models can realize advanced visual synthesis performance, underscoring the superiority and versatility of our method. Code is available at https://github.com/FoundationVision/OmniTokenizer.

Related papers

• Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization [52.63845811751936]
  Video pre-training is challenging due to the modeling of its dynamics video. In this paper, we address such limitations in video pre-training with an efficient video decomposition. Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-02-05T16:30:49Z)
• Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation [122.63617171522316]
  Large Language Models (LLMs) are the dominant models for generative tasks in language. We introduce MAGVIT-v2, a video tokenizer designed to generate concise and expressive tokens for both videos and images.
  arXiv  Detail & Related papers  (2023-10-09T14:10:29Z)
• UMIFormer: Mining the Correlations between Similar Tokens for Multi-View 3D Reconstruction [9.874357856580447]
  We propose a novel transformer network for Unstructured Multiple Images (UMIFormer) It exploits transformer blocks for decoupled intra-view encoding and designed blocks for token rectification. All tokens acquired from various branches are compressed into a fixed-size compact representation.
  arXiv  Detail & Related papers  (2023-02-27T17:27:45Z)
• OmniVL:One Foundation Model for Image-Language and Video-Language Tasks [117.57580168859512]
  We present OmniVL, a new foundation model to support both image-language and video-language tasks using one universal architecture. We demonstrate, for the first time, such a paradigm benefits both image and video tasks, as opposed to the conventional one-directional transfer. We introduce a novel unified vision-language contrastive (UniVLC) loss to leverage image-text, video-text, image-label (e.g., image classification), video-label (e.g., video action recognition) data together.
  arXiv  Detail & Related papers  (2022-09-15T17:59:59Z)
• Frozen CLIP Models are Efficient Video Learners [86.73871814176795]
  Video recognition has been dominated by the end-to-end learning paradigm. Recent advances in Contrastive Vision-Language Pre-training pave the way for a new route for visual recognition tasks. We present Efficient Video Learning -- an efficient framework for directly training high-quality video recognition models.
  arXiv  Detail & Related papers  (2022-08-06T17:38:25Z)
• Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers [51.581926074686535]
  We present a new perspective of achieving image synthesis by viewing this task as a visual token generation problem. The proposed TokenGAN has achieved state-of-the-art results on several widely-used image synthesis benchmarks.
  arXiv  Detail & Related papers  (2021-11-05T12:57:50Z)
• Unified Image and Video Saliency Modeling [21.701431656717112]
  We ask: Can image and video saliency modeling be approached via a unified model? We propose four novel domain adaptation techniques and an improved formulation of learned Gaussian priors. We integrate these techniques into a simple and lightweight encoder-RNN-decoder-style network, UNISAL, and train it jointly with image and video saliency data. We evaluate our method on the video saliency datasets DHF1K, Hollywood-2 and UCF-Sports, and the image saliency datasets SALICON and MIT300.
  arXiv  Detail & Related papers  (2020-03-11T18:28:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.