AI Paper Atlas

Research map / Image generation / Image restoration

CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering

Zhengqi Li, Noah Snavely

ECCV 2018 · Image generation › Image restoration · approach: Dehazing and deraining · 159 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
render with high-quality BDPT and simple tone mapping (CGI) instead of PBRS renderings (ablation)CGI-trained network · IIW testWHDR: 26.1% -> 17.8%Improved
compute scale-invariant MSE in linear domain instead of log domain (ablation)CGI-trained network · IIW testWHDR: 22.7% -> 17.8%Improved
add multi-scale gradient matching loss (ablation)CGI-trained network · IIW testWHDR: 19.7% -> 17.8%Improved
add ordinal loss derived from CGI ground truth (ablation)CGI-trained network · IIW testWHDR: 19.9% -> 17.8%Improved
add reflectance smoothness loss (ablation)network trained on All · IIW testWHDR: 16.1% -> 15.5%Improved
add augmented IIW annotations to CGI training (ablation)Ours · IIW testWHDR: 17.8% -> 16.2%Improved
add SAW data to CGI+IIW(A) trainingOurs · IIW testWHDR: 16.2% -> 15.5%Improved
apply guided filter post-processingOurs (CGI) · IIW testWHDR: 17.8% -> 17.1%Improved
add SAW data (with SAW losses) to CGI+IIW(A)Ours · SAW test (challenge AP)AP%: 94.69 -> 97.93Improved
add shading smoothness loss (ablation)network trained on CGI+IIW(A)+SAW · SAW test (challenge AP)AP%: 94.87 -> 97.93Improved
add gradient matching loss (ablation)CGI-trained network · SAW test (challenge AP)AP%: 93.74 -> 94.05Improved
render with CGI pipeline instead of PBRS (ablation)CGI-trained network · SAW test (challenge AP)AP%: 87.09 -> 94.05Improved

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