AI Paper Atlas

Research map / 3D vision / Depth and stereo

Rendering-Aware HDR Environment Map Prediction from a Single Image

Jun-Peng Xu, Chenyu Zuo, Fang-Lue Zhang, Miao Wang

AAAI 2022 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 19 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 proposed two-stage method instead of the strongest relighting baselineHDR environment map prediction · Laval Indoor HDR test set, relightingRMSE: 0.0583 -> 0.0494Improved
use the proposed two-stage method instead of the strongest relighting baselineHDR environment map prediction · Laval Indoor HDR test set, relightingsi-RMSE: 0.0583 -> 0.0420Improved
use the proposed two-stage method instead of the strongest relighting baselineHDR environment map prediction · Laval Indoor HDR test set, relightingAngular Error: 10.31 -> 7.35Improved
use the proposed two-stage method instead of the strongest environment-map baselineHDR environment map prediction · Laval Indoor HDR test set, environment mapRMSE: 0.2117 -> 0.1877Improved
use the proposed two-stage method instead of the strongest environment-map baselineHDR environment map prediction · Laval Indoor HDR test set, environment mapsi-RMSE: 0.1539 -> 0.1411Improved
use the proposed two-stage method instead of the strongest environment-map baselineHDR environment map prediction · Laval Indoor HDR test set, environment mapAngular Error: 30.23 -> 27.20Improved
add logarithmic intensity loss to GMLight (ablation)DLA-SK SG regression · Laval Indoor HDRRME: 1.385 -> 1.120Improved
add sum loss alongside logarithmic intensity loss (ablation)DLA-SK SG regression · Laval Indoor HDRRME: 1.120 -> 1.233Hurt
add Transformer to DLA-SK (ablation)SG regression with GMLight loss · Laval Indoor HDRRME: 1.385 -> 1.041Improved
add Transformer and logarithmic intensity loss to DLA-SK (ablation)SG regression · Laval Indoor HDRRME: 1.120 -> 0.639Improved
add Transformer and sum loss to DLA-SK with logarithmic loss (ablation)SG regression · Laval Indoor HDRRME: 1.233 -> 0.363Improved
use coarse-to-fine SH coefficient weighting instead of standard coefficient MSE (ablation)SH regression · Laval Indoor HDR, rendered objectsRMSE: 0.0452 -> 0.0437Improved

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