BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions
Wonyong Seo, Jihyong Oh, Munchurl Kim
Abstract
Existing Video Frame interpolation (VFI) models tend to suffer from time-to-location ambiguity when trained with video of non-uniform motions, such as accelerating, decelerating, and changing directions, which often yield blurred interpolated frames. In this paper, we propose (i) a novel motion description map, Bidirectional Motion field (BiM), to effectively describe non-uniform motions; (ii) a BiMguided Flow Net (BiMFN) with Content-Aware Upsampling Network (CAUN) for precise optical flow estimation; and
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext beff9f0f-19da-49a1-a59b-fe40a24590b8Cited by top-tier papers6
- Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion TransformersXinyu Peng, Han Li, Yuyang Huang, Ziyang Zheng et al.CVPR 2026 · 4 citations
- LVTINO: LAtent Video consisTency INverse sOlver for High Definition Video RestorationAlessio Spagnoletti, Andres Almansa, Marcelo PereyraICLR 2026 · 2 citations
- Time-Specialized Event-Image Alignment for Blur-to-Video DecompositionZhijing Sun, Senyan Xu, Ruixuan Jiang, Kean Liu et al.CVPR 2026
- HeroGS: Hierarchical Guidance for Robust 3D Gaussian Splatting under Sparse ViewsJiashu Li, Xumeng Han, Zhaoyang Wei, Zipeng Wang et al.CVPR 2026
- SpeedVFI: One-step Diffusion for Efficient Video Frame InterpolationGanggui Ding, Xiaogang Xu, Hao Chen, Chunhua ShenICML 2026
Builds on21
- Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu et al.ICCV 2021 · 31,683 citations
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
- Channel Attention Is All You Need for Video Frame InterpolationMyungsub Choi, Heewon Kim, Bohyung Han, Ning Xu et al.AAAI 2020 · 362 citations
- XVFI: eXtreme Video Frame InterpolationHyeonjun Sim, Jihyong Oh, Munchurl KimICCV 2021 · 207 citations
- Asymmetric Bilateral Motion Estimation for Video Frame InterpolationJunheum Park, Chul Lee, Chang-Su KimICCV 2021 · 186 citations
Related papers
- Generalizable Implicit Motion Modeling for Video Frame InterpolationZujin Guo, Wei Li, Chen Change LoyNeurIPS 2024 · 24 citations
- VTinker: Guided Flow Upsampling and Texture Mapping for High-Resolution Video Frame InterpolationChenyang Wu, Jiayi Fu, Chun-Le Guo, Shuhao Han et al.AAAI 2026 · 2 citations
- Event-based Video Frame Interpolation with Cross-Modal Asymmetric Bidirectional Motion FieldsTaewoo Kim, Yujeong Chae, Hyun-Kurl Jang, Kuk-Jin YoonCVPR 2023
- Learning to Handle Large Obstructions in Video Frame InterpolationLibo Long, Xiao Hu, Jochen LangACM MM 2024
- TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear MotionHaoyue Liu, Jinghan Xu, Yi Chang, Hanyu Zhou et al.CVPR 2025
