Research map / Architectures and efficiency / CNN design
End-To-End Projector Photometric Compensation
Bingyao Huang, Haibin Ling
Check 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 |
|---|---|---|---|
| include the camera-captured surface image as an input (ablation) | CompenNet · Projector compensation benchmark, 24 setups, 500 training images | PSNR: 20.2618 -> 21.7998 | Improved |
| include the camera-captured surface image as an input (ablation) | CompenNet · Projector compensation benchmark, 24 setups, 500 training images | RMSE: 0.1698 -> 0.1425 | Improved |
| include the camera-captured surface image as an input (ablation) | CompenNet · Projector compensation benchmark, 24 setups, 500 training images | SSIM: 0.7209 -> 0.7523 | Improved |
| pre-train on 500 images projected onto a white surface (ablation) | CompenNet · Projector compensation benchmark, 24 setups, 32 training pairs and 500 iterations | PSNR: 19.6767 -> 20.3423 | Improved |
| pre-train on 500 images projected onto a white surface (ablation) | CompenNet · Projector compensation benchmark, 24 setups, 32 training pairs and 500 iterations | RMSE: 0.1863 -> 0.1688 | Improved |
| pre-train on 500 images projected onto a white surface (ablation) | CompenNet · Projector compensation benchmark, 24 setups, 32 training pairs and 500 iterations | SSIM: 0.6788 -> 0.7165 | Improved |
| use L1 plus SSIM loss instead of pixel-wise L1 loss (ablation) | CompenNet · Projector compensation benchmark, 24 setups, 500 training images | PSNR: 21.1782 -> 21.7998 | Improved |
| use L1 plus SSIM loss instead of pixel-wise L2 loss (ablation) | CompenNet · Projector compensation benchmark, 24 setups, 500 training images | PSNR: 20.7927 -> 21.7998 | Improved |
| use L1 plus SSIM loss instead of SSIM loss alone (ablation) | CompenNet · Projector compensation benchmark, 24 setups, 500 training images | PSNR: 21.0134 -> 21.7998 | Improved |
| use L1 plus SSIM loss instead of SSIM loss alone (ablation) | CompenNet · Projector compensation benchmark, 24 setups, 500 training images | SSIM: 0.7591 -> 0.7523 | Hurt |
| increase training images from 125 to 500 (ablation) | CompenNet · Projector compensation benchmark, 24 setups | PSNR: 21.0542 -> 21.7998 | Improved |
| increase training images from 125 to 500 (ablation) | CompenNet · Projector compensation benchmark, 24 setups | SSIM: 0.7314 -> 0.7523 | Improved |
Closest papers by meaning
- CompenNet++: End-to-End Full Projector Compensation (ICCV 2019 · similarity 0.94)
- End-to-End Full Projector Compensation (TPAMI 2021 · similarity 0.94)
- Breaking the Scalability Limit of Multi-Projector Calibration with Embedded Cameras (CVPR 2026 · similarity 0.82)
- Global Latent Neural Rendering (CVPR 2024 · similarity 0.80)
- Projection Head is Secretly an Information Bottleneck (ICLR 2025 · similarity 0.80)
- Understanding the Role of the Projector in Knowledge Distillation (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.
