Research map / Video / Video segmentation and tracking
TimeLens-XL: Real-time Event-based Video Frame Interpolation with Large Motion
Shi Guo, Yutian Chen, Tianfan Xue, Jinwei Gu, Yongrui Ma
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 |
|---|---|---|---|
| estimate motion trajectory iteratively in small steps instead of two-segment flow, at larger interpolation scale | TLXNet · GOPRO x32 | PSNR (dB): 33.92 -> 34.89 | Improved |
| use larger configuration TLXNet+ instead of TLXNet (ablation) | TimeLens-XL · GOPRO x16 | PSNR (dB): 36.01 -> 36.52 | Improved |
| use TLXNet instead of CBMNet on low-noise real data | BS-ERGB x2 · BS-ERGB x2 | PSNR (dB): 29.10 -> 28.55 | Hurt |
| use TLXNet+ instead of CBMNet | BS-ERGB x2 · BS-ERGB x2 | PSNR (dB): 29.10 -> 29.46 | Improved |
| use TLXNet instead of CBMNet in efficiency | Event-VFI at 1280x720 x16 · Runtime | runtime (ms): 990.75 -> 37.36 | Improved |
| use TLXNet instead of CBMNet for MACs | Event-VFI at 1280x720 x16 · Computation | MACs: 2549.18G -> 271.45G | Improved |
| use TLXNet instead of TimeLens | HQ-EVFI x8 · HQ-EVFI x8 | PSNR (dB): 33.88 -> 33.99 | No clear effect |
| add events to RGB-only interpolation | RIFE · GOPRO x16 | PSNR (dB): 24.74 -> 36.01 | Improved |
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.
- TimeLens — Time Lens: Event-Based Video Frame Interpolation (CVPR 2021) · better on 8 of 8 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
- TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion (CVPR 2025 · similarity 0.91)
- Video Frame Interpolation via Direct Synthesis with the Event-based Reference (CVPR 2024 · similarity 0.91)
- Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation (CVPR 2025 · similarity 0.89)
- TTA-EVF: Test-Time Adaptation for Event-based Video Frame Interpolation via Reliable Pixel and Sample Estimation (CVPR 2024 · similarity 0.87)
- BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions (CVPR 2025 · similarity 0.87)
- Sparse Global Matching for Video Frame Interpolation with Large Motion (CVPR 2024 · 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.
