BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation
Junheum Park, Jintae Kim, Chang-Su Kim
2023Year
16Top-tier citations
Abstract
233px 163px ๐ฑ ๐กโ1 ๐ฑ ๐กโ1 ๐ฑ ๐กโ1 23.67dB / 0.8137 26.64dB / 0.8634 20.21dB / 0.7516 Blended Input Figure 1. Examples of 4K video frame interpolation results, obtained by ABME [1], XVFI [2], and the proposed BiFormer. 4K video frame interpolation is challenging due to large motion magnitudes, e.g. hundreds of pixels. PSNR/SSIM scores are presented within the interpolation results, and the estimated motion fields Vtโ1 are at the bottom row.
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 7b8e4bc9-485b-4a56-a4d7-4da26fd86582Cited by top-tier papers16
- PMQ-VE: Progressive Multi-Frame Quantization for Video EnhancementZhanfeng Feng, Long Peng, Xin Di, Yong Guo et al.NeurIPS 2025 ยท 17 citations
- Sparse Global Matching for Video Frame Interpolation with Large MotionChunxu Liu, Guozhen Zhang, Rui Zhao, Limin WangCVPR 2024 ยท 17 citations
- Disentangled Motion Modeling for Video Frame InterpolationJaihyun Lew, Jooyoung Choi, Chaehun Shin, Dahuin Jung et al.AAAI 2025 ยท 11 citations
- High-Resolution Frame Interpolation with Patch-based Cascaded DiffusionJunhwa Hur, Charles Herrmann, Saurabh Saxena, Janne Kontkanen et al.AAAI 2025 ยท 8 citations
- Spatio-Temporal Interactive Learning for Efficient Image Reconstruction of Spiking CamerasBin Fan, Jiaoyang Yin, Yuchao Dai, Chao Xu et al.NeurIPS 2024 ยท 7 citations
Builds on18
- Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu et al.ICCV 2021 ยท 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 ยท 21,477 citations
- Swin Transformer V2: Scaling Up Capacity and ResolutionZe Liu, Han Hu, Yutong Lin, Zhuliang Yao et al.CVPR 2022 ยท 2,138 citations
- Twins: Revisiting the Design of Spatial Attention in Vision TransformersXiangxiang Chu, Zhi Tian, Yuqing Wang, Bo Zhang et al.NeurIPS 2021 ยท 1,388 citations
- Channel Attention Is All You Need for Video Frame InterpolationMyungsub Choi, Heewon Kim, Bohyung Han, Ning Xu et al.AAAI 2020 ยท 362 citations
Related papers
- XVFI: eXtreme Video Frame InterpolationHyeonjun Sim, Jihyong Oh, Munchurl KimICCV 2021 ยท 207 citations
- Hierarchical Flow Diffusion for Efficient Frame InterpolationYang Hai, Guo Wang, Tan Su, Wenjie Jiang et al.CVPR 2025
- Repurposing Pre-trained Video Diffusion Models for Event-based Video InterpolationJingxi Chen, Brandon Y. Feng, Haoming Cai, Tianfu Wang et al.CVPR 2025
- Asymmetric Bilateral Motion Estimation for Video Frame InterpolationJunheum Park, Chul Lee, Chang-Su KimICCV 2021 ยท 186 citations
- Video Frame Interpolation with TransformerLiying Lu, Ruizheng Wu, Huaijia Lin, Jiangbo Lu et al.CVPR 2022 ยท 128 citations
