Research map / Video / Video segmentation and tracking
UDC-VIT: A Real-World Video Dataset for Under-Display Cameras
Kyusu Ahn, JiSoo Kim, Sangik Lee, HyunGyu Lee, Byeonghyun Ko, Chanwoo Park, Jaejin Lee
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 |
|---|---|---|---|
| train on real UDC-VIT instead of synthetic-trained VidUDC33K model | DDRNet · UDC-VIT test | PSNR: 11.20 -> 24.68 | Improved |
| train on UDC-VIT instead of VidUDC33K, test on VidUDC33K | DISCNet · VidUDC33K test | PSNR: 28.89 -> 18.73 | Hurt |
| fine-tune UDC-SIT-trained UDC-UNet on 10% UDC-VIT (ablation) | UDC-UNet · UDC-VIT test | PSNR: 17.21 -> 24.94 | Improved |
| fine-tune on 20% instead of 10% UDC-VIT (ablation) | UDC-UNet · UDC-VIT test | PSNR: 24.94 -> 25.41 | Improved |
| fine-tune VidUDC33K-trained DDRNet on UDC-VIT (ablation) | DDRNet · UDC-VIT test | PSNR: 11.20 -> 21.92 | Improved |
| fine-tune UDC-VIT-trained UDC-UNet on VidUDC33K (ablation) | UDC-UNet · VidUDC33K test | PSNR: 19.84 -> 29.57 | Improved |
| apply DFT alignment to UDC-VIT (ablation) | UDC-VIT · LoFTR PCK@0.003 | PCK: 85.10 -> 92.12 | Improved |
| restore UDC input with UDC-UNet before face recognition | face recognition models · UDC-VIT FR | accuracy: 64.5 -> 82.2 | Improved |
| use real-world UDC-VIT instead of VidUDC33K to benchmark models | six restoration models · UDC-VIT vs VidUDC33K | PSNR: 16.26 -> 26.22 | Mixed |
Closest papers by meaning
- UDC-SIT: A Real-World Dataset for Under-Display Cameras (NeurIPS 2023 · similarity 0.92)
- Decoupling Degradations with Recurrent Network for Video Restoration in Under-Display Camera (AAAI 2024 · similarity 0.89)
- Panel-Specific Degradation Representation for Raw Under-Display Camera Image Restoration (ECCV 2024 · similarity 0.89)
- Generating Aligned Pseudo-Supervision From Non-Aligned Data for Image Restoration in Under-Display Camera (CVPR 2023 · similarity 0.87)
- Under-Display Camera Image Restoration with Scattering Effect (ICCV 2023 · similarity 0.86)
- Towards a Universal Synthetic Video Detector: From Face or Background Manipulations to Fully AI-Generated Content (CVPR 2025 · similarity 0.83)
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.
