AI Paper Atlas

Research map / 3D vision / Depth and stereo

Gradient-Based Uncertainty for Monocular Depth Estimation

Julia Hornauer, Vasileios Belagiannis

ECCV 2022 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth

This paper tried a common change: Add dropout

add inference-time dropout uncertainty · KITTI stereo supervision · AUSE RMSE: 2.523 -> 3.366 Hurt

What 795 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 gradient-based uncertaintyMonodepth2 Post · KITTI monocular supervisionAUSE RMSE: 2.864 -> 0.540Improved
add gradient-based uncertaintyMonodepth2 Self · KITTI monocular supervisionAUSE Abs Rel: 0.030 -> 0.024Improved
add gradient-based uncertaintyMonodepth2 Post · KITTI stereo supervisionAUSE RMSE: 2.523 -> 0.510Improved
add gradient-based uncertaintyMonodepth2 Self · KITTI stereo supervisionAUSE Abs Rel: 0.022 -> 0.022No clear effect
add gradient-based uncertaintyMonodepth2 Post · NYU Depth V2AUSE Abs Rel: 0.066 -> 0.061Improved
add gradient-based uncertaintyMonodepth2 Log · NYU Depth V2AUSE RMSE: 0.159 -> 0.176Hurt
add inference-time dropout uncertaintyMonodepth2 Post · KITTI stereo supervisionAUSE RMSE: 2.523 -> 3.366Hurt
add inference-time dropout uncertaintyMonodepth2 Post · KITTI monocular supervisionAUSE RMSE: 2.864 -> 0.871Improved
use flip reference loss instead of ground-truth loss (ablation)Gradient uncertainty Post · NYU Depth V2AUSE Abs Rel: 0.020 -> 0.061Hurt
use flip instead of grayscale reference (ablation)Gradient uncertainty Post · NYU Depth V2AUSE Abs Rel: 0.067 -> 0.061Improved
use flip instead of 20 degree rotation reference (ablation)Gradient uncertainty Post · NYU Depth V2AUSE Abs Rel: 0.076 -> 0.061Improved
use flip instead of Gaussian noise reference (ablation)Gradient uncertainty Post · NYU Depth V2AUSE RMSE: 0.261 -> 0.252Improved

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