ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2506.01004
39
0

Motion-Aware Concept Alignment for Consistent Video Editing

1 June 2025
Tong Zhang
Juan Carlos León Alcázar
Bernard Ghanem
    DiffMVGen
ArXiv (abs)PDFHTML
Main:8 Pages
7 Figures
4 Tables
Appendix:7 Pages
Abstract

We introduce MoCA-Video (Motion-Aware Concept Alignment in Video), a training-free framework bridging the gap between image-domain semantic mixing and video. Given a generated video and a user-provided reference image, MoCA-Video injects the semantic features of the reference image into a specific object within the video, while preserving the original motion and visual context. Our approach leverages a diagonal denoising schedule and class-agnostic segmentation to detect and track objects in the latent space and precisely control the spatial location of the blended objects. To ensure temporal coherence, we incorporate momentum-based semantic corrections and gamma residual noise stabilization for smooth frame transitions. We evaluate MoCA's performance using the standard SSIM, image-level LPIPS, temporal LPIPS, and introduce a novel metric CASS (Conceptual Alignment Shift Score) to evaluate the consistency and effectiveness of the visual shifts between the source prompt and the modified video frames. Using self-constructed dataset, MoCA-Video outperforms current baselines, achieving superior spatial consistency, coherent motion, and a significantly higher CASS score, despite having no training or fine-tuning. MoCA-Video demonstrates that structured manipulation in the diffusion noise trajectory allows for controllable, high-quality video synthesis.

View on arXiv
@article{zhang2025_2506.01004,
  title={ Motion-Aware Concept Alignment for Consistent Video Editing },
  author={ Tong Zhang and Juan C Leon Alcazar and Bernard Ghanem },
  journal={arXiv preprint arXiv:2506.01004},
  year={ 2025 }
}
Comments on this paper