计算机科学
插值(计算机图形学)
人工智能
生成语法
帧(网络)
计算机视觉
生成模型
运动插值
连贯性(哲学赌博策略)
运动(物理)
语义学(计算机科学)
算法
光流
图像缩放
模式识别(心理学)
作者
Yiying Wei,Hadi Amirpour,Christian Timmerer
标识
DOI:10.1109/icassp55912.2026.11463375
摘要
Video frame interpolation (VFI) aims to generate intermediate frames between given keyframes to enhance temporal resolution and visual smoothness. While conventional optical flow–based methods and recent generative approaches achieve promising results, they often struggle with large displacements, failing to maintain temporal coherence and semantic consistency. In this work, we propose dual-guided generative frame interpolation (DGFI), a framework that integrates semantic guidance from vision-language models and flow guidance into a pre-trained diffusion-based image-to-video (I2V) generator. Specifically, DGFI extracts textual descriptions and injects multimodal embeddings to capture high-level semantics, while estimated motion guidance provides smooth transitions. Experiments on public datasets demonstrate the effectiveness of our dual-guided method over the state-of-the-art approaches.
科研通智能强力驱动
Strongly Powered by AbleSci AI