AI Paper Atlas

Research map / 3D vision / Depth and stereo

Illuminant Spectra-Based Source Separation Using Flash Photography

Zhuo Hui, Kalyan Sunkavalli, Sunil Hadap, Aswin C. Sankaranarayanan

CVPR 2018 · 3D vision › Depth and stereo · approach: Photometric stereo · 14 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
Use the flash/no-flash pair and Hull Constraint for source separationIlluminant source separation · Figure 4 two-light sceneSNR: 20.43 dB vs. 16.96 dB; 20.43 dB vs. 10.13 dBImproved
Use flash/no-flash source separation to create inputs for photometric stereoTwo-shot photometric stereo · Real-object photometric stereomean angular error: 23.42 -> 0.57Improved
Use weighted PCA with camera spectral response weights to learn the reflectance and illumination bases (ablation)Illuminant source separation · Basis selectionsource separation performanceImproved
Replace weighted PCA with unweighted PCA for basis learning (ablation)Illuminant source separation · Basis selectionsource separation performanceHurt
Replace weighted PCA with joint learning of subspaces (ablation)Illuminant source separation · Basis selectionsource separation performanceHurt

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