Research map / Video / Video segmentation and tracking
HR-INR: Continuous Space-Time Video Super-Resolution via Event Camera
Yunfan Lu, Yusheng Wang, Zipeng Wang, Pengteng Li, Bin Yang, Hui Xiong
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 event input (ablation) | HR-INR · Adobe-Average (4x VSR, 7-skip VFI) | PSNR: 26.84 -> 29.69 | Improved |
| add temporal pyramid representation (TPR) on top of events (ablation) | HR-INR · Adobe-Average (4x VSR, 7-skip VFI) | PSNR: 29.69 -> 31.11 | Improved |
| add TPR on BS-ERGB 1-skip (ablation) | HR-INR · BS-ERGB 1-skip VFI | PSNR: 28.25 -> 29.66 | Improved |
| add TPR on BS-ERGB 3-skip (ablation) | HR-INR · BS-ERGB 3-skip VFI | PSNR: 26.65 -> 28.59 | Improved |
| increase TPR levels from 3 to 7 (ablation) | HR-INR · Adobe-Average (4x VSR, 7-skip VFI) | PSNR: 29.93 -> 31.11 | Improved |
| increase TPR moments Mp from 9 to 18 (ablation) | HR-INR · Adobe-Average (4x VSR, 7-skip VFI) | PSNR: 31.11 -> 31.18 | No clear effect |
| use learned temporal embedding instead of sinusoid (ablation) | HR-INR · Adobe-Average (4x VSR, 7-skip VFI) | PSNR: 30.42 -> 31.11 | Improved |
| increase temporal dimension from 320 to 640 (ablation) | HR-INR · Adobe-Average (4x VSR, 7-skip VFI) | PSNR: 28.44 -> 31.11 | Improved |
| increase temporal dimension to 960 (ablation) | HR-INR · Adobe-Average (4x VSR, 7-skip VFI) | training stability | Hurt |
| increase input frames from 2 to 4 (ablation) | HR-INR · Adobe-Average (4x VSR, 7-skip VFI) | PSNR: 30.41 -> 31.11 | Improved |
| increase input frames from 3 to 4 (ablation) | HR-INR · Adobe-Average (4x VSR, 7-skip VFI) | PSNR: 30.72 -> 31.11 | Improved |
| use HR-INR instead of MoTIF | HR-INR vs MoTIF · GoPro-Average (4x VSR, 7-skip VFI) | PSNR: 30.04 -> 32.13 | Improved |
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.
- MoTIF — MoTIF: Learning Motion Trajectories with Local Implicit Neural Functions for Continuous Space-Time Video Super-Resolution (ICCV 2023) · better on 9 of 9 shared results
- TimeLens++ — Time Lens: Event-Based Video Frame Interpolation (CVPR 2021) · better on 2 of 2 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
- Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolution (CVPR 2023 · similarity 0.93)
- Time Without Time: Pseudo-Temporal Representation for Space-Time Super-Resolution (CVPR 2026 · similarity 0.91)
- EvEnhancer: Empowering Effectiveness, Efficiency and Generalizability for Continuous Space-Time Video Super-Resolution with Events (CVPR 2025 · similarity 0.91)
- BF-STVSR: B-Splines and Fourier---Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution (CVPR 2025 · similarity 0.90)
- EvSTVSR: Event Guided Space-Time Video Super-Resolution (AAAI 2025 · similarity 0.90)
- Event-based Video Super-Resolution via State Space Models (CVPR 2025 · similarity 0.88)
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.
