One-Shot Flow, Any-Time Frame: A Bidirectional Warping Framework for Event-Based Video Frame Interpolation
Linghui Fu, Yuhan Liu, Hao Chen, Zhen Yang, Yongjian Deng
摘要
Video Frame Interpolation (VFI) is a crucial task in video processing. Flow-based methods, despite their success, are constrained by a fundamental dilemma: forward warping is efficient but prone to artifacts, while backward warping yields higher quality at a significant computational cost, especially for multi-frame interpolation. This trade-off is a major bottleneck. To overcome this, we introduce ``One-Shot Flow, Any-Time Frame," a novel framework for Event-based VFI (E-VFI) that achieves both high efficiency and superior quality for arbitrary-time interpolation. Our framework uniquely computes a comprehensive motion trajectory representation in a single pass using a Bidirectional Flow Estimation Block (BiFEB), leveraging the high temporal resolution of event data. Subsequently, our Flow Query (FQ) module can instantly retrieve the bidirectional optical flow for any timestamp, enabling the generation of any number of frames without repeated computation. Finally, a novel Bidirectional Warping (BiW) mechanism intelligently fuses the strengths of both warping directions, effectively mitigating artifacts and producing high-fidelity results. Extensive experiments show that our approach consistently surpasses state-of-the-art E-VFI methods in both reconstruction quality and inference efficiency, representing a substantial advance in efficient and high-quality event-based video interpolation. The code will be released after acceptance.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper24
- Channel Attention Is All You Need for Video Frame InterpolationMyungsub Choi, Heewon Kim, Bohyung Han, Ning Xu 等AAAI 2020 · 被引用 362 次
- IFRNet: Intermediate Feature Refine Network for Efficient Frame InterpolationLingtong Kong, Boyuan Jiang, Donghao Luo, Wenqing Chu 等CVPR 2022 · 被引用 166 次
- Video Frame Interpolation via Deformable Separable ConvolutionXianhang Cheng, Zhenzhong ChenAAAI 2020 · 被引用 153 次
- Time Lens++: Event-based Frame Interpolation with Parametric Nonlinear Flow and Multi-scale FusionStepan Tulyakov, Alfredo Bochicchio, Daniel Gehrig, Stamatios Georgoulis 等CVPR 2022 · 被引用 126 次
- Video Frame Interpolation TransformerZhihao Shi, Xiangyu Xu, Xiaohong Liu, Jun Chen 等CVPR 2022 · 被引用 117 次
相关 Paper
- Event-based Video Frame Interpolation with Cross-Modal Asymmetric Bidirectional Motion FieldsTaewoo Kim, Yujeong Chae, Hyun-Kurl Jang, Kuk-Jin YoonCVPR 2023
- Video Frame Interpolation via Direct Synthesis with the Event-based ReferenceYuhan Liu, Yongjian Deng, Hao Chen, Zhen YangCVPR 2024
- TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear MotionHaoyue Liu, Jinghan Xu, Yi Chang, Hanyu Zhou 等CVPR 2025
- Event-Based Frame Interpolation with Ad-hoc DeblurringLei Sun, Christos Sakaridis, Jingyun Liang, Peng Sun 等CVPR 2023
- Many-to-many Splatting for Efficient Video Frame InterpolationPing Hu, Simon Niklaus, Stan Sclaroff, Kate SaenkoCVPR 2022 · 被引用 63 次
