RAGME: Retrieval Augmented Video Generation for Enhanced Motion Realism

• URL: http://arxiv.org/abs/2504.06672v1
• Date: Wed, 09 Apr 2025 08:14:05 GMT
• Title: RAGME: Retrieval Augmented Video Generation for Enhanced Motion Realism
• Authors: Elia Peruzzo, Dejia Xu, Xingqian Xu, Humphrey Shi, Nicu Sebe,
• Abstract summary: We propose a framework to improve the realism of motion in generated videos.<n>We advocate for the incorporation of a retrieval mechanism during the generation phase.<n>Our pipeline is designed to apply to any text-to-video diffusion model.
• Score: 73.38167494118746
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Video generation is experiencing rapid growth, driven by advances in diffusion models and the development of better and larger datasets. However, producing high-quality videos remains challenging due to the high-dimensional data and the complexity of the task. Recent efforts have primarily focused on enhancing visual quality and addressing temporal inconsistencies, such as flickering. Despite progress in these areas, the generated videos often fall short in terms of motion complexity and physical plausibility, with many outputs either appearing static or exhibiting unrealistic motion. In this work, we propose a framework to improve the realism of motion in generated videos, exploring a complementary direction to much of the existing literature. Specifically, we advocate for the incorporation of a retrieval mechanism during the generation phase. The retrieved videos act as grounding signals, providing the model with demonstrations of how the objects move. Our pipeline is designed to apply to any text-to-video diffusion model, conditioning a pretrained model on the retrieved samples with minimal fine-tuning. We demonstrate the superiority of our approach through established metrics, recently proposed benchmarks, and qualitative results, and we highlight additional applications of the framework.

Related papers

• ReVision: High-Quality, Low-Cost Video Generation with Explicit 3D Physics Modeling for Complex Motion and Interaction [22.420752010237052]
  We introduce ReVision, a plug-and-play framework that explicitly integrates parameterized 3D physical knowledge into a conditional video generation model. We validate the effectiveness of our approach on Stable Video Diffusion, where ReVision significantly improves motion fidelity and coherence. Our results suggest that, by incorporating 3D physical knowledge, even a relatively small video diffusion model can generate complex motions and interactions with greater realism and controllability.
  arXiv  Detail & Related papers  (2025-04-30T17:59:56Z)
• Semantic Latent Motion for Portrait Video Generation [19.56640370303683]
  Semantic Latent Motion (SeMo) is a compact and expressive motion representation.<n>SeMo follows an effective three-step framework: Abstraction, Reasoning, and Generation.<n>Our approach surpasses state-of-the-art models with an 81% win rate in realism.
  arXiv  Detail & Related papers  (2025-03-13T06:43:21Z)
• VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models [71.9811050853964]
  VideoJAM is a novel framework that instills an effective motion prior to video generators.<n>VideoJAM achieves state-of-the-art performance in motion coherence.<n>These findings emphasize that appearance and motion can be complementary and, when effectively integrated, enhance both the visual quality and the coherence of video generation.
  arXiv  Detail & Related papers  (2025-02-04T17:07:10Z)
• TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation [97.96178992465511]
  We argue that generated videos should incorporate the emergence of new concepts and their relation transitions like in real-world videos as time progresses. To assess the Temporal Compositionality of video generation models, we propose TC-Bench, a benchmark of meticulously crafted text prompts, corresponding ground truth videos, and robust evaluation metrics.
  arXiv  Detail & Related papers  (2024-06-12T21:41:32Z)
• 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)
• LaMD: Latent Motion Diffusion for Image-Conditional Video Generation [63.34574080016687]
  latent motion diffusion (LaMD) framework consists of a motion-decomposed video autoencoder and a diffusion-based motion generator. LaMD generates high-quality videos on various benchmark datasets, including BAIR, Landscape, NATOPS, MUG and CATER-GEN.
  arXiv  Detail & Related papers  (2023-04-23T10:32:32Z)
• Latent Video Diffusion Models for High-Fidelity Long Video Generation [58.346702410885236]
  We introduce lightweight video diffusion models using a low-dimensional 3D latent space. We also propose hierarchical diffusion in the latent space such that longer videos with more than one thousand frames can be produced. Our framework generates more realistic and longer videos than previous strong baselines.
  arXiv  Detail & Related papers  (2022-11-23T18:58:39Z)
• Transformation-based Adversarial Video Prediction on Large-Scale Data [19.281817081571408]
  We focus on the task of video prediction, where given a sequence of frames extracted from a video, the goal is to generate a plausible future sequence. We first improve the state of the art by performing a systematic empirical study of discriminator decompositions. We then propose a novel recurrent unit which transforms its past hidden state according to predicted motion-like features.
  arXiv  Detail & Related papers  (2020-03-09T10:52:25Z)

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.