AI Paper Atlas

Research map / 3D vision / Depth and stereo

EMLight: Lighting Estimation via Spherical Distribution Approximation

Fangneng Zhan, Changgong Zhang, Yingchen Yu, Yuan Chang, Shijian Lu, Feiying Ma, Xuansong Xie

AAAI 2021 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 54 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 spherical Gaussian representation with spherical distribution representation (ablation)EMLight regression network · Laval Indoor HDR test, diffuseRMSE: 0.204 -> 0.133Improved
replace L2 loss with spherical mover's loss (SML) (ablation)EMLight spherical-distribution regression · Laval Indoor HDR test, diffuseRMSE: 0.133 -> 0.080Improved
add the neural projector (ablation)EMLight with spherical distribution and SML · Laval Indoor HDR test, diffuseRMSE: 0.080 -> 0.062Improved
replace SML with cross-entropy loss (ablation)EMLight* · Laval Indoor HDR testRMSE: 0.074 -> 0.102Hurt
replace spherical convolution with normal convolution (ablation)EMLight* · Laval Indoor HDR testRMSE: 0.074 -> 0.086Hurt
reduce anchor points from 128 to 64 (ablation)EMLight* · Laval Indoor HDR testRMSE: 0.074 -> 0.091Hurt
increase anchor points from 128 to 196 (ablation)EMLight* · Laval Indoor HDR testsi-RMSE: 0.058 -> 0.055Improved
increase anchor points from 128 to 196 (ablation)EMLight* · Laval Indoor HDR testRMSE: 0.074 -> 0.076No clear effect
use EMLight instead of the strongest reported baselinelighting estimation · Laval Indoor HDR test, diffuseRMSE: 0.084 -> 0.062Improved
use EMLight instead of the strongest reported baselinelighting estimation · Laval Indoor HDR test, diffuseAMT: 33.5\% -> 40.0\%Improved

Later papers that compared with this method

2 later accepted papers report EMlight as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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