Research map / Image generation / Image restoration
CompenNet++: End-to-End Full Projector Compensation
Bingyao Huang, Haibin Ling
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 the grid refinement network to CompenNet++ (ablation) | CompenNet++ · Full projector compensation benchmark (#Train=500) | PSNR: 20.9172 -> 21.1127 | Improved |
| add the grid refinement network to CompenNet++ (ablation) | CompenNet++ · Full projector compensation benchmark (#Train=48) | PSNR: 19.4139 -> 19.8552 | Improved |
| add the grid refinement network to CompenNet++ (ablation) | CompenNet++ · Full projector compensation benchmark (#Train=500) | SSIM: 0.7113 -> 0.7269 | Improved |
| use end-to-end CompenNet++ instead of two-step CompenNet with structured light warping | projector full compensation · Full projector compensation benchmark (#Train=500) | PSNR: 20.9552 -> 21.1127 | Improved |
| use end-to-end CompenNet++ instead of two-step CompenNet with structured light warping | projector full compensation · Full projector compensation benchmark (#Train=48) | PSNR: 20.2023 -> 19.8552 | Hurt |
| replace CompenNet++ with general image-to-image model Pix2pix with structured light warping | projector full compensation · Full projector compensation benchmark (#Train=500) | PSNR: 21.1127 -> 19.4160 | Hurt |
| train TPS on colorful textured images instead of plain color images | TPS with structured light · Full projector compensation benchmark | PSNR: 16.7271 -> 17.9746 | Improved |
| use the fast variant (1,000 iterations, batch 24, 48 images) of CompenNet++ | CompenNet++ · Full projector compensation benchmark | PSNR: 19.8552 -> 19.9696 | Mixed |
| use the faster variant (500 iterations, batch 16, 48 images) of CompenNet++ | CompenNet++ · Full projector compensation benchmark (#Train=48) | PSNR: 19.8552 -> 19.2536 | Hurt |
| increase training set size from 48 to 500 images | CompenNet++ · Full projector compensation benchmark | PSNR: 19.8552 -> 21.1127 | Improved |
Closest papers by meaning
- End-to-End Full Projector Compensation (TPAMI 2021 · similarity 0.97)
- End-To-End Projector Photometric Compensation (CVPR 2019 · similarity 0.94)
- Breaking the Scalability Limit of Multi-Projector Calibration with Embedded Cameras (CVPR 2026 · similarity 0.84)
- Simultaneous Geometric and Radiometric Calibration of a Projector-Camera Pair (CVPR 2017 · similarity 0.82)
- World Tracing: Pixel-Aligned Geometry Beyond the Visible (NeurIPS 2026 · similarity 0.81)
- CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformers (AAAI 2024 · similarity 0.80)
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.
