Research map / Video / Video segmentation and tracking
A Dual Camera System for High Spatiotemporal Resolution Video Acquisition
Ming Cheng, Zhan Ma, M. Salman Asif, Yiling Xu, Haojie Liu, Wenbo Bao, Jun Sun
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 AWnet instead of CrossNet | AWnet · Vimeo90K test 4x SR | PSNR: 39.17 -> 39.88 | Improved |
| use AWnet instead of CrossNet | AWnet · Vimeo90K test 8x SR | PSNR: 36.15 -> 36.63 | Improved |
| add a 1/16 or 1/64 downscaled target frame to interpolation | AWnet · Vimeo90K test frame interpolation | PSNR: 33.46 -> 36.63 | Improved |
| use EDSR rather than bicubic upscaling filter (ablation) | AWnet · Vimeo90K test 4x SR | PSNR: 39.75 -> 39.88 | No clear effect |
| use EDSR rather than bicubic upscaling filter (ablation) | AWnet · Vimeo90K test 8x SR | PSNR: 36.47 -> 36.63 | No clear effect |
| use multiple references instead of a single reference (ablation) | AWnet · Vimeo90K test 8x, 7-frame sequences | PSNR: 35.33 -> 36.21 | Improved |
| use AWFusion instead of convolution-based direct prediction (ablation) | AWnet · Vimeo90K test 4x SR | PSNR: 39.67 -> 39.88 | Improved |
| use AWFusion instead of convolution-based direct prediction (ablation) | AWnet · Vimeo90K test 8x SR | PSNR: 36.45 -> 36.63 | Improved |
| use AWnet instead of CrossNet at large parallax | AWnet · Stanford Light Field 8x, parallax (5,0) | PSNR: 35.15 -> 36.47 | Improved |
| use AWnet instead of CrossNet at large baseline | AWnet · KITTI 8x SR | PSNR: 24.92 -> 26.01 | Improved |
| use AWnet instead of CrossNet | AWnet · Flower(1,1) 8x SR | PSNR: 39.35 -> 39.29 | Hurt |
| use AWnet instead of CrossNet | AWnet · Flower(7,7) 8x SR | PSNR: 34.11 -> 34.53 | Improved |
Closest papers by meaning
- Pix2HDR - A Pixel-Wise Acquisition and Deep Learning-Based Synthesis Approach for High-Speed HDR Videos (TPAMI 2024 · similarity 0.85)
- Real-Time Video Super-Resolution With Spatio-Temporal Networks and Motion Compensation (CVPR 2017 · similarity 0.85)
- HFR and HDR Video from Multi-Attenuated Spikes Using a Rapidly Rotating SpokeND Filter (CVPR 2026 · similarity 0.85)
- Joint Framework for Single Image Reconstruction and Super-Resolution With an Event Camera (TPAMI 2021 · similarity 0.85)
- Learning to Super Resolve Intensity Images From Events (CVPR 2020 · similarity 0.84)
- Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network (CVPR 2024 · similarity 0.84)
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.
