AI Paper Atlas

Research map / 3D vision / Face and shape

An Approximate Shading Model with Detail Decomposition for Object Relighting

Zicheng Liao, Kevin Karsch, Hongyi Zhang, David Forsyth

IJCV 2018 · 3D vision › Face and shape · approach: Textured mesh generation · 12 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 ground truth shading to derive detail layers instead of defaultOurs (oracle weights) · MIT Intrinsic (Lab illumination)re-rendering MSE: 0.0586 -> 0.0228Improved
use Barron and Malik shading estimation for detail derivation instead of default (ablation)Ours (regress) · MIT Intrinsic (Natural illumination)re-rendering MSE: 0.0358 -> 0.0320Improved
replace Barron and Malik SIRFS shape with approximate shading modelOurs (regress) · MIT Intrinsic (Natural illumination)re-rendering MSE: 0.0172 -> 0.0358Hurt
replace Barron and Malik SIRFS shape with approximate shading modelOurs (regress) · MIT Intrinsic (Lab illumination)re-rendering MSE: 0.0372 -> 0.0641Mixed
use SIRFS-stereo base shape instead of SFC (ablation)Ours (oracle) · Relighting dataset (10 objects x 10 lights)re-rendering MSE: 0.0295 -> 0.0194Improved
use Kinect depth instead of SFC base shape (ablation)Ours (default) · Relighting dataset (10 objects x 10 lights)re-rendering MSE: 0.0723 -> 0.0732No clear effect
use SIRFS depth instead of SFC base shape (ablation)Ours (oracle) · Relighting dataset (10 objects x 10 lights)re-rendering MSE: 0.0295 -> 0.0334Hurt
add parametric shading detail layer (ablation)Ours insertion · User study detail layers% preferred: 61% of 764 viewed pairsImproved
add geometric detail layer on top of parametric detail (ablation)Ours insertion · User study detail layers% preferred: 65% of 756 viewed pairsImproved
insert real image fragments with approximate model instead of 3D synthetic models (Karsch et al.)insertion · User study% chosen as real: 34% -> 44%Improved

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