Research map / Video / Video segmentation and tracking
Video Object Segmentation-aware Video Frame Interpolation
Jun-Sang Yoo, Hongjae Lee, Seung-Won Jung
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 VOS-based segmentation and bi-directional consistency losses to VFI training | AdaCoF · DAVIS 2016 | J&F: 85.9 -> 87.0 | Improved |
| add VOS-VFI training | AdaCoF · DAVIS 2016 | PSNR: 25.11 -> 25.03 | No clear effect |
| add VOS-VFI training | AdaCoF, CDFI, IFRNet · DAVIS foreground PSNR | foreground PSNR: 25.74 -> 25.80 (CDFI, DAVIS 2016) | Improved |
| add VOS-VFI training | CDFI · Vimeo90K / UCF101 / Xiph perceptual metrics | NIQE, PI, NIMA: PI 3.832 -> 3.822 (Vimeo90K) | Improved |
| add VOS-VFI training to the interpolation model | CDFI · VOT2018 tracking | AUC: 58.7 -> 60.1 | Improved |
| add VOS-VFI training | IFRNet · VOT2018 | AUC: 59.5 -> 60.3 | Improved |
| add VOS-VFI training | CDFI · Linemod pose estimation | REP-20px: 63.24 -> 64.09 | Improved |
| add segmentation loss (forward and backward) (ablation) | CDFI · DAVIS 2016 | J&F: 86.9 -> 87.2 | Improved |
| add bi-directional consistency loss (ablation) | CDFI · DAVIS 2016 | J&F: 86.9 -> 87.5 | Improved |
| use both losses together versus either alone (ablation) | CDFI · DAVIS 2016 | J&F: 87.7 vs 87.2 and 87.5 | Improved |
| use a single-frame segmentation module instead of a VOS model (ablation) | CDFI-VOS · DAVIS 2016 | J&F: 87.7 -> 86.8 | Hurt |
| swap the pretrained VOS model (STCN vs other VOS models) (ablation) | CDFI-VOS · DAVIS 2016 | J&F: 87.7 vs 87.4 and 87.7 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- CDFI — CDFI: Compression-Driven Network Design for Frame Interpolation (CVPR 2021) · better on 5 of 5 shared results
- IFRNet — IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation (CVPR 2022) · better on 3 of 3 shared results
- AdaCoF — AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation (CVPR 2020) · better on 2 of 3 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
- Perception-Oriented Video Frame Interpolation via Asymmetric Blending (CVPR 2024 · similarity 0.87)
- LDMVFI: Video Frame Interpolation with Latent Diffusion Models (AAAI 2024 · similarity 0.87)
- Disentangled Motion Modeling for Video Frame Interpolation (AAAI 2025 · similarity 0.86)
- Point-VOS: Pointing Up Video Object Segmentation (CVPR 2024 · similarity 0.86)
- Video Frame Interpolation via Direct Synthesis with the Event-based Reference (CVPR 2024 · similarity 0.86)
- BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions (CVPR 2025 · similarity 0.86)
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.
