AI Paper Atlas

Research map / 3D vision / Face and shape

Material Editing Using a Physically Based Rendering Network

Guilin Liu, Duygu Ceylan, Ersin Yumer, Jimei Yang, Jyh-Ming Lien

ICCV 2017 · 3D vision › Face and shape · approach: Textured mesh generation · 94 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
add rendering layer with perceptual loss to material prediction module (ablation)material prediction module · Material prediction with GT normals and illuminationrendered image L2: 544.1 -> 355.5Improved
add rendering layer with perceptual loss to material prediction module (ablation)material prediction module · Material prediction with GT normals and illuminationrendered image SSIM: 0.9297 -> 0.9517Improved
add rendering layer with perceptual loss to material prediction module (ablation)material prediction module · Material prediction with GT normals and illuminationmaterial coefficient L2: 4.1038 -> 4.8144Hurt
add rendering layer with perceptual loss to normal prediction module (ablation)normal prediction module · Surface normal prediction (car)rendered image L2: 313.2058 -> 238.4619Improved
add rendering layer with perceptual loss to normal prediction module (ablation)normal prediction module · Surface normal prediction (car)rendered image SSIM: 0.9441 -> 0.9625Improved
add rendering layer with perceptual loss to normal prediction module (ablation)normal prediction module · Surface normal prediction (car)normals cosine: 0.9105 -> 0.9050No clear effect
add post-optimization of intrinsic properties (ablation)our network · Material transfer, synthetic testL2 error: 805.2 -> 530.9Improved
add post-optimization of intrinsic properties (ablation)our network · Material transfer, synthetic testSSIM: 0.9408 -> 0.9557Improved
add post-optimization of intrinsic properties (ablation)Baseline 2 (independent predictions) · Material transfer, synthetic testL2 error: 886.9 -> 1273.7Hurt
replace independent L2-trained normal, material, illumination networks with joint network with rendering layermaterial transfer pipeline · Material transfer, synthetic testL2 error: 886.9 -> 805.2Improved
use rendering-layer network instead of encoder-decoder feature swappingmaterial transfer pipeline · Material transfer, synthetic testL2 error: 1076.7 -> 805.2Improved

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