AI Paper Atlas

Research map / 3D vision / Face and shape

Metadata-Based RAW Reconstruction via Implicit Neural Functions

Leyi Li, Huijie Qiao, Qi Ye, Qinmin Yang

CVPR 2023 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 5 citations (OpenAlex)

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 changedWhereMeasuredEffect
Replace CAM with INF using uniform RAW samplingRAW reconstruction · CAM dataset [24], three camerasPSNR: 49.57 -> 53.53; 51.54 -> 56.71; 53.11 -> 58.36Improved
Replace CAM with INF on full-resolution imagesRAW reconstruction · NUS [9], three camerasPSNR: 49.51 -> 61.48; 52.87 -> 63.38; 53.34 -> 63.80Improved
Use INF instead of RBF interpolation (ablation)RAW reconstruction with sRGB input · RAW reconstructionPSNR: 29.10 -> 59.62Improved
Use INF instead of RBF interpolation (ablation)RAW reconstruction with coordinate input · RAW reconstructionPSNR: 21.71 -> 31.09Improved
Use INF instead of RBF interpolation with combined inputs (ablation)RAW reconstruction · RAW reconstructionPSNR: 49.69 -> 60.91Improved
Separate sRGB values and coordinates into distinct branches rather than combine them (ablation)INF · RAW reconstructionPSNR: 60.91 -> 62.24Improved
Add sRGB values as input alongside coordinates (ablation)INF · RAW reconstructionPSNR: 31.09 -> 60.91Improved
Use patch-specific reconstruction instead of larger patches (ablation)INF · RAW reconstruction, regularization λ=(0.0001, 0.1, 0.001)PSNR: 59.64 -> 62.24Improved
Use patch size ×1 instead of ×2 (ablation)INF · RAW reconstruction, regularization λ=(0.0001, 0.1, 0.001)PSNR: 62.24 -> 62.58Improved
Add regularization with λ=(0.0001, 0.1, 0.001) at patch size ×2 (ablation)INF · RAW reconstructionPSNR: 49.17 -> 62.24Improved
Use ReLU activation instead of sine activation (ablation)INF · RAW reconstructionPSNRHurt
Use ReLU activation instead of sine activation (ablation)INF · Guided depth super-resolution on MiddleburyRMSE: 2.50 -> 2.39; 3.06 -> 2.69; 5.23 -> 3.57Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy