AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation

Gwangbin Bae, Ignas Budvytis, Roberto Cipolla

ICCV 2021 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Priors and functional variational uncertainty · 114 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 angular vonMF NLL instead of vonMF NLL (ablation)baseline encoder-decoder · ScanNet (20% train subset, ablation)mean angular error: 14.10 -> 13.82Improved
add learned attenuation to the angular loss (AL to NLL-AngMF) (ablation)baseline encoder-decoder · ScanNet (20% train subset, ablation)mean angular error: 13.45 -> 13.82 mean; 6.70 -> 6.60 medianMixed
add pixel-wise MLP decoder modules (ablation)NLL-AngMF · ScanNet (20% train subset, ablation)mean angular error: 13.82 -> 13.59Improved
add uncertainty-guided sampling to MLP training (ablation)NLL-AngMF + MLPs · ScanNet (20% train subset, ablation)mean angular error: 13.59 -> 13.17Improved
importance-sample uncertain pixels (beta_UG 0.0 to 0.7) (ablation)full method · ScanNet (20% train subset, ablation)mean angular error: 13.58 -> 13.17Improved
sample only highest-uncertainty pixels (beta_UG 1.0 vs 0.7) (ablation)full method · ScanNet (20% train subset, ablation)mean angular error: 13.17 -> 13.26Hurt
use the proposed method versus GeoNet++Ours · NYUv2 (trained on NYUv2)mean angular error: 18.5 -> 14.9Improved
use the proposed method versus TiltedSNOurs · ScanNet (full train)mean angular error: 12.6 -> 11.8Improved
cross-dataset transfer ScanNet to NYUv2 versus TiltedSNOurs · NYUv2 (trained on ScanNet)accuracy within 11.25 deg: 59.8 -> 59.0No clear effect
use predicted NLL uncertainty instead of dropout plus augmentationOurs (NLL-AngMF) · NYUv2 uncertaintyAUSC mean: 8.16 -> 6.83Improved
AngMF instead of vonMF for uncertainty (ablation)Ours · NYUv2 uncertaintyAUSC mean / AUSE mean: 7.03 -> 6.83 AUSC; 2.11 -> 2.13 AUSEMixed
combine test-time dropout and augmentation (ablation)Drop · NYUv2 uncertaintyAUSC mean: 9.01 -> 8.16Improved

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