EGVD: Event-Guided Video Diffusion Model for Physically Realistic Large-Motion Frame Interpolation

Our approach significantly outperforms existing methods in handling large motion and challenging lighting conditions. The video demonstrates the superiority of EGVD in generating physically realistic intermediate frames, particularly in scenarios with complex motion patterns.

Video frame interpolation (VFI) in scenarios with large motion remains challenging due to motion ambiguity between frames. While event cameras can capture high temporal resolution motion information, existing event-based VFI methods struggle with limited training data and complex motion patterns. In this paper, we introduce Event-Guided Video Diffusion Model (EGVD), a novel framework that leverages the powerful priors of pre-trained stable video diffusion models alongside the precise temporal information from event cameras. Our approach features a Multi-modal Motion Condition Generator (MMCG) that effectively integrates RGB frames and event signals to guide the diffusion process, producing physically realistic intermediate frames. We employ a selective fine-tuning strategy that preserves spatial modeling capabilities while efficiently incorporating event-guided temporal information. We incorporate input-output normalization techniques inspired by recent advances in diffusion modeling to enhance training stability across varying noise levels. To improve generalization, we construct a comprehensive dataset combining both real and simulated event data across diverse scenarios. Extensive experiments on both real and simulated datasets demonstrate that EGVD significantly outperforms existing methods in handling large motion and challenging lighting conditions, achieving substantial improvements in perceptual quality metrics (27.4% better LPIPS on Prophesee and 24.1% on BSRGB) while maintaining competitive fidelity measures.

Our EGVD framework introduces a novel approach that leverages both event camera data and stable video diffusion models to achieve high-quality frame interpolation. The key component of our method is the Multi-modal Motion Condition Generator (MMCG), which effectively integrates RGB frames and event signals to guide the diffusion process.

• • A novel Multi-Modal Motion Condition Generator (MMCG) that integrates event information into the SVD framework to improve the interpolation of large motions.
• • A two-stage training strategy that first trains the conditioning generator independently, followed by fine-tuning the SVD model to adapt to Event-VFI.
• • A diverse and comprehensive training dataset that combines real-world and synthetic event-RGB data, improving the generalization ability of our model.
• • Extensive experimental results demonstrate that our approach outperforms existing methods, particularly in large-motion and low-light scenarios.