Research map / 3D vision / Depth and stereo
Color Pass-Through via Camera-Display Coupling
Ruikang Li, Molin Li, Jiarui Wu, Zhe Wei, Pengpeng Liu, Tianfan Xue
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 camera-null color correction (ablation) | Color Pass-Through · ColorChecker 24 patches (Huawei) | PSNR: 27.32 -> 28.65 | Improved |
| add camera-null color correction (ablation) | Color Pass-Through · ColorChecker 24 patches (Huawei) | DeltaE mean: 6.49 -> 5.18 | Improved |
| add camera-null color correction (ablation) | Color Pass-Through · ColorChecker 24 patches (Xiaomi) | DeltaE mean: 5.97 -> 4.79 | Improved |
| add camera-null color correction (ablation) | Color Pass-Through · ColorChecker 24 patches (Huawei) | STRESS: 17.27 -> 17.48 | No clear effect |
| use learned camera-display projector instead of default smartphone camera output | Color Pass-Through · ColorChecker 24 patches (Huawei) | PSNR: 13.78 -> 27.32 | Improved |
| use learned projector instead of per-scene color-checker calibration | Color Pass-Through · ColorChecker 24 patches (Xiaomi) | PSNR: 16.36 -> 29.10 | Improved |
| use lightweight MLP with positional encoding and green-channel AvgPool as projector | Color Pass-Through · Camera-display projector fit | PSNR: 31.12 -> 32.13 | Improved |
| add TV smoothness loss on coefficient (ablation) | a_i predictor · Camera-null coefficient a_i learning | PSNR(a_hat, a): 29.00 -> 29.68 | Improved |
| add spectral reconstruction loss (ablation) | a_i predictor · Camera-null coefficient a_i learning | PSNR(a_hat, a): 29.42 -> 29.68 | Improved |
| add coefficient losses on top of spectral loss only (ablation) | a_i predictor · Camera-null coefficient a_i learning | PSNR(s_hat, s): 14.94 -> 31.95 | Improved |
| train projector on only 100 images (ablation) | Color Pass-Through · Camera-display projector fit | color preservation | No clear effect |
| use camera-display projector alone with a DSLR observer (ablation) | Color Pass-Through · DSLR observer | color shift | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CSRNet — CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes (CVPR 2018) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Measuring Perceptual Color Differences of Smartphone Photographs (TPAMI 2023 · similarity 0.85)
- Color3D: Controllable and Consistent 3D Colorization with Personalized Colorizer (ICLR 2026 · similarity 0.84)
- Perceiving Better Moments: Cover Frame Reselection and Enhancement for Live Photos with the Live2K Dataset (ECCV 2026 · similarity 0.84)
- DiffRAW: Leveraging Diffusion Model to Generate DSLR-Comparable Perceptual Quality sRGB from Smartphone RAW Images (AAAI 2024 · similarity 0.83)
- GCC: Generative Color Constancy via Diffusing a Color Checker (CVPR 2025 · similarity 0.83)
- CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation (NeurIPS 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.
