Research map / Video / Video segmentation and tracking
BMBC: Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation
Junheum Park, Keunsoo Ko, Chul Lee, Chang-Su Kim
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add bilateral-motion candidates to four approximated candidates (ablation) | BMBC · Vimeo90K | PSNR: 34.72 -> 34.93 | Improved |
| add bilateral-motion candidates to four approximated candidates (ablation) | BMBC · UCF101 | PSNR: 34.99 -> 35.12 | Improved |
| add two approximated candidates to bilateral candidates (ablation) | BMBC · Vimeo90K | PSNR: 34.93 -> 34.95 | Improved |
| add four approximated candidates (instead of two) to bilateral candidates (ablation) | BMBC · Vimeo90K | PSNR: 34.95 -> 35.01 | Improved |
| add four approximated candidates to bilateral candidates (ablation) | BMBC · UCF101 | PSNR: 35.12 -> 35.15 | Improved |
| feed input frames to filter generation network (ablation) | BMBC · Vimeo90K | PSNR: 34.81 -> 34.96 | Improved |
| feed input frames to filter generation network (ablation) | BMBC · UCF101 | PSNR: 34.98 -> 35.08 | Improved |
| additionally feed context maps to filter generation network (ablation) | BMBC · Vimeo90K | PSNR: 34.96 -> 35.01 | Improved |
| additionally feed context maps to filter generation network (ablation) | BMBC · UCF101 | PSNR: 35.08 -> 35.15 | Improved |
| increase blending kernel size from 3x3 to 7x7 (ablation) | BMBC · Vimeo90K | PSNR: 34.90 -> 34.98 | No clear effect |
| replace DAIN with BMBC | video interpolation · Vimeo90K | PSNR: 34.71 -> 35.01 | Improved |
| replace DAIN with BMBC | video interpolation · Middlebury Evaluation | average IE: 4.86 -> 4.48 | Improved |
Later papers that compared with this method
6 later accepted papers report BMBC as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.
- SVFI: Spiking-Based Video Frame Interpolation for High-Speed Motion (AAAI 2023 · better on 1 of 1 shared result)
- FILM: Frame Interpolation for Large Motion (ECCV 2022 · better on 3 of 3 shared results)
- Learning Cross-Video Neural Representations for High-Quality Frame Interpolation (ECCV 2022 · better on 2 of 2 shared results)
- Real-Time Intermediate Flow Estimation for Video Frame Interpolation (ECCV 2022 · better on 1 of 1 shared result)
- Asymmetric Bilateral Motion Estimation for Video Frame Interpolation (ICCV 2021 · better on 5 of 6 shared results)
- Time Lens: Event-Based Video Frame Interpolation (CVPR 2021 · better on 4 of 4 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MEMC-Net* — MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement (TPAMI 2019) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Asymmetric Bilateral Motion Estimation for Video Frame Interpolation (ICCV 2021 · similarity 0.90)
- BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation (CVPR 2023 · similarity 0.89)
- Channel Attention Is All You Need for Video Frame Interpolation (AAAI 2020 · similarity 0.87)
- Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation (CVPR 2018 · similarity 0.87)
- BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions (CVPR 2025 · similarity 0.85)
- ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler (ICLR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
