AI Paper Atlas

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

Bayesian Deep Basis Fitting for Depth Completion With Uncertainty

Chao Qu, Wenxin Liu, Camillo J. Taylor

ICCV 2021 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Priors and functional variational uncertainty · 30 citations (OpenAlex)

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 Bayesian treatment with shared prior on top of deep basis fitting (ablation)dbf · VKITTI2 5% sparsityAUSE: 0.148 -> 0.110Improved
add Bayesian treatment with shared prior on top of deep basis fitting (ablation)dbf · VKITTI2 5% sparsityNLL: -2.489 -> -2.596Improved
add Bayesian treatment with shared prior on top of deep basis fitting (ablation)dbf · VKITTI2 500 sparse depthsAUCE: 0.051 -> 0.014Improved
add Bayesian treatment with shared prior on top of deep basis fitting (ablation)dbf · VKITTI2 1% sparsityNLL: -1.670 -> -1.707No clear effect
add Bayesian treatment with shared prior on top of deep basis fitting (ablation)dbf · NYU-V2 1% sparsityNLL: -2.381 -> -2.374No clear effect
drop sparse depth network input and use depths only in the fitting step (ablation)bdbf (rgbd) · VKITTI2 50 sparse depthsMAE: 4.098 -> 3.725Improved
drop sparse depth network input and use depths only in the fitting step (ablation)bdbf (rgbd) · VKITTI2 500 sparse depthsMAE: 2.015 -> 2.569Hurt
add a predictive variance head with NLL loss to snapshot ensemble (ablation)snap · VKITTI2 5% sparsityAUSE: 0.445 -> 0.142Improved
add snapshot ensembling to predictive (log) method (ablation)log · VKITTI2 5% sparsityAUSE: 0.149 -> 0.142No clear effect
replace log baseline by bdbf for uncertaintylog · VKITTI2 5% sparsityNLL: -1.421 -> -2.596Improved
replace log baseline by bdbf under domain shift (train VKITTI2, test KITTI)log · KITTI (shifted)NLL: -0.755 -> -2.381Improved
use bdbf instead of monocular log baseline with no sparse depthslog (rgb) · NYU-V2 0 sparse depthsMAE: 0.366 -> 0.664Hurt

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