AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning Single Camera Depth Estimation Using Dual-Pixels

Rahul Garg, Neal Wadhwa, Sameer Ansari, Jonathan T. Barron

ICCV 2019 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 131 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 affine-invariant loss instead of scale-invariant loss (ablation)DPNet (RGB+DP input) · Dual-pixel dataset (our depth)geometric mean: .0477 -> .0422Improved
use affine-invariant loss instead of no invariance (ablation)DPNet (RGB+DP input) · Dual-pixel dataset (our depth)geometric mean: .1530 -> .0422Improved
use affine-invariant loss instead of scale-invariant loss (ablation)VGG (RGB+DP input) · Dual-pixel dataset (our depth)geometric mean: .0535 -> .0446Improved
use affine-invariant loss instead of scale-invariant loss (ablation)Godard et al. (ResNet50) · Dual-pixel dataset (our depth)geometric mean: .0613 -> .0592Improved
use affine-invariant loss instead of scale-invariant loss (ablation)Garg et al. (ResNet50) · Dual-pixel dataset (our depth)geometric mean: .0613 -> .0584Improved
use affine-invariant loss instead of scale-invariant loss (ablation)DPNet (RGB input) · Dual-pixel dataset (our depth)geometric mean: .1047 -> .1014Improved
add dual-pixel data to RGB input (ablation)DPNet with affine invariance · Dual-pixel dataset (our depth)geometric mean: .1014 -> .0422Improved
use 3D assisted loss instead of folded loss (ablation)DPNet · Dual-pixel dataset (our depth)AIWE(1): .0225 -> .0175Improved
use 3D assisted loss instead of folded loss (ablation)DPNet · Dual-pixel dataset (our depth)1 - |rho_s|: .195 -> .139Improved
train on all 4 alternative views instead of stereo views only (ablation)DPNet · Dual-pixel dataset (our depth)AIWE(1): .0218 -> .0175Improved
evaluate on photos from phones unseen in training (extended test set) vs standard test setDPNet · Dual-pixel dataset (our depth)AIWE(1): .0175 -> .0188Hurt
use small DPNet instead of larger VGG under affine invarianceDPNet vs VGG (RGB+DP) · Dual-pixel dataset (our depth)geometric mean: .0446 -> .0422Improved

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