MOVi: Training-free Text-conditioned Multi-Object Video Generation

• URL: http://arxiv.org/abs/2505.22980v1
• Date: Thu, 29 May 2025 01:41:10 GMT
• Title: MOVi: Training-free Text-conditioned Multi-Object Video Generation
• Authors: Aimon Rahman, Jiang Liu, Ze Wang, Ximeng Sun, Jialian Wu, Xiaodong Yu, Yusheng Su, Vishal M. Patel, Zicheng Liu, Emad Barsoum,
• Abstract summary: We present a training-free approach for multi-object video generation that leverages the open world knowledge of diffusion models and large language models (LLMs)<n>We use an LLM as the director'' of object trajectories, and apply the trajectories through noise re-initialization to achieve precise control of realistic movements.<n>Experiments validate the effectiveness of our training free approach in significantly enhancing the multi-object generation capabilities of existing video diffusion models.
• Score: 43.612899589093075
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in diffusion-based text-to-video (T2V) models have demonstrated remarkable progress, but these models still face challenges in generating videos with multiple objects. Most models struggle with accurately capturing complex object interactions, often treating some objects as static background elements and limiting their movement. In addition, they often fail to generate multiple distinct objects as specified in the prompt, resulting in incorrect generations or mixed features across objects. In this paper, we present a novel training-free approach for multi-object video generation that leverages the open world knowledge of diffusion models and large language models (LLMs). We use an LLM as the ``director'' of object trajectories, and apply the trajectories through noise re-initialization to achieve precise control of realistic movements. We further refine the generation process by manipulating the attention mechanism to better capture object-specific features and motion patterns, and prevent cross-object feature interference. Extensive experiments validate the effectiveness of our training free approach in significantly enhancing the multi-object generation capabilities of existing video diffusion models, resulting in 42% absolute improvement in motion dynamics and object generation accuracy, while also maintaining high fidelity and motion smoothness.

Related papers

• TransFlow: Motion Knowledge Transfer from Video Diffusion Models to Video Salient Object Detection [14.635179908525389]
  We present TransFlow, which transfers motion knowledge from pre-trained video diffusion models to generate realistic training data for video salient object detection.<n>Our method achieves improved performance across multiple benchmarks, demonstrating effective motion knowledge transfer.
  arXiv  Detail & Related papers  (2025-07-26T04:30:44Z)
• GENMO: A GENeralist Model for Human MOtion [64.16188966024542]
  We present GENMO, a unified Generalist Model for Human Motion that bridges motion estimation and generation in a single framework.<n>Our key insight is to reformulate motion estimation as constrained motion generation, where the output motion must precisely satisfy observed conditioning signals.<n>Our novel architecture handles variable-length motions and mixed multimodal conditions (text, audio, video) at different time intervals, offering flexible control.
  arXiv  Detail & Related papers  (2025-05-02T17:59:55Z)
• ObjectMover: Generative Object Movement with Video Prior [69.75281888309017]
  We present ObjectMover, a generative model that can perform object movement in challenging scenes.<n>We show that with this approach, our model is able to adjust to complex real-world scenarios.<n>We propose a multi-task learning strategy that enables training on real-world video data to improve the model generalization.
  arXiv  Detail & Related papers  (2025-03-11T04:42:59Z)
• Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback [130.090296560882]
  We investigate the use of feedback to enhance the object dynamics in text-to-video models.<n>We show that our method can effectively optimize a wide variety of rewards, with binary AI feedback driving the most significant improvements in video quality for dynamic interactions.
  arXiv  Detail & Related papers  (2024-12-03T17:44:23Z)
• MoTrans: Customized Motion Transfer with Text-driven Video Diffusion Models [59.10171699717122]
  MoTrans is a customized motion transfer method enabling video generation of similar motion in new context.<n> multimodal representations from recaptioned prompt and video frames promote the modeling of appearance.<n>Our method effectively learns specific motion pattern from singular or multiple reference videos.
  arXiv  Detail & Related papers  (2024-12-02T10:07:59Z)
• TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models [75.20168902300166]
  We propose TrackDiffusion, a novel video generation framework affording fine-grained trajectory-conditioned motion control. A pivotal component of TrackDiffusion is the instance enhancer, which explicitly ensures inter-frame consistency of multiple objects. generated video sequences by our TrackDiffusion can be used as training data for visual perception models.
  arXiv  Detail & Related papers  (2023-12-01T15:24:38Z)
• Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation [26.292052071093945]
  We propose an unsupervised method to generate videos from a single frame and a sparse motion input. Our trained model can generate unseen realistic object-to-object interactions. We show that YODA is on par with or better than state of the art video generation prior work in terms of both controllability and video quality.
  arXiv  Detail & Related papers  (2023-06-06T19:50:02Z)

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.