Research map / Video / Video segmentation and tracking
Self-supervised Learning to Bring Dual Reversed Rolling Shutter Images Alive
Wei Shang, Dongwei Ren, Chaoyu Feng, Xiaotao Wang, Lei Lei, Wangmeng Zuo
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 self-distillation loss L_sd in a second training stage (ablation) | SelfDRSC · RS-GOPRO | PSNR: 28.411 -> 28.704 | Improved |
| add intermediate-frame loss L_sme to start/end loss L_se (ablation) | SelfDRSC · RS-GOPRO | PSNR: 20.643 -> 28.411 | Improved |
| add start/end loss L_se to intermediate-only loss L_sme (ablation) | SelfDRSC · RS-GOPRO | PSNR: 23.241 -> 28.411 | Improved |
| use CFR and backwarping instead of linear approximation and splatting (ablation) | bidirectional distortion warping · RS-GOPRO | PSNR: 26.267 -> 28.411 | Improved |
| use CFR and backwarping instead of flow reversal and backwarping (ablation) | bidirectional distortion warping · RS-GOPRO | PSNR: 27.175 -> 28.411 | Improved |
| use pre-trained PWC-Net instead of GMFlow or RIFE flow for GS-frame flow (ablation) | bidirectional distortion warping · RS-GOPRO | PSNR: 25.670 -> 28.411 (vs GMFlow-sintel) | Improved |
| self-supervised training without ground-truth GS frames vs supervised IFED | SelfDRSC · RS-GOPRO | PSNR: 30.681 -> 28.704 | Hurt |
| self-supervised training vs supervised IFED on real-world data | SelfDRSC · Real-world RS data | NRQM: 5.953 -> 7.683 | Improved |
Closest papers by meaning
- Bringing Rolling Shutter Images Alive with Dual Reversed Distortion (ECCV 2022 · similarity 0.90)
- Neural Global Shutter: Learn To Restore Video From a Rolling Shutter Camera With Global Reset Feature (CVPR 2022 · similarity 0.89)
- Learning Adaptive Warping for Real-World Rolling Shutter Correction (CVPR 2022 · similarity 0.89)
- Rolling Shutter Inversion: Bring Rolling Shutter Images to High Framerate Global Shutter Video (TPAMI 2022 · similarity 0.88)
- Inverting a Rolling Shutter Camera: Bring Rolling Shutter Images to High Framerate Global Shutter Video (ICCV 2021 · similarity 0.88)
- Rolling Shutter Correction with Intermediate Distortion Flow Estimation (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.
