Research map / Video / Video segmentation and tracking
MoTIF: Learning Motion Trajectories with Local Implicit Neural Functions for Continuous Space-Time Video Super-Resolution
Yi-Hsin Chen, Si-Cun Chen, Yi-Hsin Chen, Yen-Yu Lin, Wen-Hsiao Peng
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 |
|---|---|---|---|
| use forward motion instead of backward motion in the space-time implicit function (ablation) | MoTIF · GoPro-Center | PSNR: 29.98 -> 31.04 | Improved |
| use explicit motion from pretrained optical flow instead of implicit motion (ablation) | MoTIF · GoPro-Center | PSNR: 30.58 -> 31.04 | Improved |
| add forward-warped features F_t for decoding (ablation) | MoTIF · Vid4 | PSNR: 22.38 -> 25.26 | Improved |
| encode flow reliability maps into motion latents (ablation) | MoTIF · Vid4 | PSNR: 25.26 -> 25.61 | Improved |
| add warped reliability map Z_t to decoder (ablation) | MoTIF · Vid4 | PSNR: 25.61 -> 25.79 | Improved |
| replace tri-linear motion interpolation with ST-INF (ablation) | MoTIF · Vid4 | PSNR: 25.57 -> 25.79 | Improved |
| use 4 reference frames instead of 2 (ablation) | MoTIF · GoPro-Average | PSNR: 30.08 -> 30.77 | Improved |
| replace VideoINR with MoTIF for temporal x6 spatial x6 | C-STVSR · GoPro | PSNR: 25.56 -> 29.36 | Improved |
| train MoTIF versus TMNet on Vid4 | MoTIF · Vid4 | PSNR: 25.96 -> 25.79 | Hurt |
| forward-warp latents once instead of backward warping twice | MoTIF · Vid4 complexity, temporal x16 spatial x4 | FPS: 29.06 -> 42.50 | Improved |
Later papers that compared with this method
5 later accepted papers report MoTIF as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- HR-INR: Continuous Space-Time Video Super-Resolution via Event Camera (IJCV 2026 · better on 9 of 9 shared results)
- Continuous Space-Time Video Super-Resolution with 3D Fourier Fields (ICLR 2026 · better on 1 of 1 shared result)
- Thermal Diffusion Matters: Infrared Spatial-Temporal Video Super-Resolution through Heat Conduction Priors (CVPR 2026 · better on 1 of 1 shared result)
- BF-STVSR: B-Splines and Fourier---Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution (CVPR 2025 · better on 8 of 8 shared results)
- Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors (ECCV 2024 · better on 3 of 3 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- VideoINR — VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution (CVPR 2022) · better on 8 of 8 shared results
- Zooming SlowMo — Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution (CVPR 2020) · better on 1 of 1 shared result
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
- HR-INR: Continuous Space-Time Video Super-Resolution via Event Camera (IJCV 2026 · similarity 0.89)
- BF-STVSR: B-Splines and Fourier---Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution (CVPR 2025 · similarity 0.89)
- Time Without Time: Pseudo-Temporal Representation for Space-Time Super-Resolution (CVPR 2026 · similarity 0.88)
- EvEnhancer: Empowering Effectiveness, Efficiency and Generalizability for Continuous Space-Time Video Super-Resolution with Events (CVPR 2025 · similarity 0.88)
- EvSTVSR: Event Guided Space-Time Video Super-Resolution (AAAI 2025 · similarity 0.85)
- Implicit Motion Function (CVPR 2024 · similarity 0.85)
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.
