Compositional Video Generation as Flow Equalization

• URL: http://arxiv.org/abs/2407.06182v1
• Date: Mon, 10 Jun 2024 16:27:47 GMT
• Title: Compositional Video Generation as Flow Equalization
• Authors: Xingyi Yang, Xinchao Wang,
• Abstract summary: Large-scale Text-to-Video (T2V) diffusion models have recently demonstrated unprecedented capability to transform natural language descriptions into stunning and photorealistic videos. Despite the promising results, these models struggle to fully grasp complex compositional interactions between multiple concepts and actions. We introduce bftextVico, a generic framework for compositional video generation that explicitly ensures all concepts are represented properly.
• Score: 72.88137795439407
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large-scale Text-to-Video (T2V) diffusion models have recently demonstrated unprecedented capability to transform natural language descriptions into stunning and photorealistic videos. Despite the promising results, a significant challenge remains: these models struggle to fully grasp complex compositional interactions between multiple concepts and actions. This issue arises when some words dominantly influence the final video, overshadowing other concepts.To tackle this problem, we introduce \textbf{Vico}, a generic framework for compositional video generation that explicitly ensures all concepts are represented properly. At its core, Vico analyzes how input tokens influence the generated video, and adjusts the model to prevent any single concept from dominating. Specifically, Vico extracts attention weights from all layers to build a spatial-temporal attention graph, and then estimates the influence as the \emph{max-flow} from the source text token to the video target token. Although the direct computation of attention flow in diffusion models is typically infeasible, we devise an efficient approximation based on subgraph flows and employ a fast and vectorized implementation, which in turn makes the flow computation manageable and differentiable. By updating the noisy latent to balance these flows, Vico captures complex interactions and consequently produces videos that closely adhere to textual descriptions. We apply our method to multiple diffusion-based video models for compositional T2V and video editing. Empirical results demonstrate that our framework significantly enhances the compositional richness and accuracy of the generated videos. Visit our website at~\href{https://adamdad.github.io/vico/}{\url{https://adamdad.github.io/vico/}}.

Related papers

• COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing [57.76170824395532]
  Video editing is an emerging task, in which most current methods adopt the pre-trained text-to-image (T2I) diffusion model to edit the source video. We propose COrrespondence-guided Video Editing (COVE) to achieve high-quality and consistent video editing. COVE can be seamlessly integrated into the pre-trained T2I diffusion model without the need for extra training or optimization.
  arXiv  Detail & Related papers  (2024-06-13T06:27:13Z)
• VideoTetris: Towards Compositional Text-to-Video Generation [45.395598467837374]
  VideoTetris is a framework that enables compositional T2V generation. We show that VideoTetris achieves impressive qualitative and quantitative results in T2V generation.
  arXiv  Detail & Related papers  (2024-06-06T17:25:33Z)
• StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation [117.13475564834458]
  We propose a new way of self-attention calculation, termed Consistent Self-Attention. To extend our method to long-range video generation, we introduce a novel semantic space temporal motion prediction module. By merging these two novel components, our framework, referred to as StoryDiffusion, can describe a text-based story with consistent images or videos.
  arXiv  Detail & Related papers  (2024-05-02T16:25:16Z)
• 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)
• FusionFrames: Efficient Architectural Aspects for Text-to-Video Generation Pipeline [4.295130967329365]
  This paper presents a new two-stage latent diffusion text-to-video generation architecture based on the text-to-image diffusion model. The design of our model significantly reduces computational costs compared to other masked frame approaches. We evaluate different configurations of MoVQ-based video decoding scheme to improve consistency and achieve higher PSNR, SSIM, MSE, and LPIPS scores.
  arXiv  Detail & Related papers  (2023-11-22T00:26:15Z)
• TokenFlow: Consistent Diffusion Features for Consistent Video Editing [27.736354114287725]
  We present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method.
  arXiv  Detail & Related papers  (2023-07-19T18:00:03Z)
• VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning [82.09856883441044]
  Video understanding relies on perceiving the global content modeling its internal connections. We propose a block-wise strategy where we mask neighboring video tokens in both spatial and temporal domains. We also add an augmentation-free contrastive learning method to further capture global content.
  arXiv  Detail & Related papers  (2021-06-21T16:48:19Z)
• Comprehensive Information Integration Modeling Framework for Video Titling [124.11296128308396]
  We integrate comprehensive sources of information, including the content of consumer-generated videos, the narrative comment sentences supplied by consumers, and the product attributes, in an end-to-end modeling framework. To tackle this issue, the proposed method consists of two processes, i.e., granular-level interaction modeling and abstraction-level story-line summarization. We collect a large-scale dataset accordingly from real-world data in Taobao, a world-leading e-commerce platform.
  arXiv  Detail & Related papers  (2020-06-24T10:38:15Z)

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.