AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

Deep Optics for Monocular Depth Estimation and 3D Object Detection

Julie Chang, Gordon Wetzstein

ICCV 2019 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 189 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
add defocus-coded optics instead of all-in-focus imagesU-Net depth estimator · NYU Depth v2RMSE_lin: 0.9556 -> 0.4814Improved
add astigmatism to the defocus lens (ablation)U-Net depth estimator · NYU Depth v2RMSE_lin: 0.4814 -> 0.4561Improved
add chromatic aberration of a singlet lens (ablation)U-Net depth estimator · NYU Depth v2RMSE_lin: 0.4561 -> 0.4496Improved
end-to-end optimize a freeform lens instead of fixed chromatic aberration (ablation)U-Net depth estimator · KITTI subsetRMSE_lin: 2.2566 -> 1.9288Improved
end-to-end optimize a freeform lens instead of fixed chromatic aberration (ablation)U-Net depth estimator · RectanglesRMSE_lin: 0.0984 -> 0.0902Improved
optimize annular lens instead of fixed chromatic aberration (ablation)U-Net depth estimator · NYU Depth v2RMSE_lin: 0.4496 -> 0.4817Hurt
optimize annular lens instead of all-in-focus imagesU-Net depth estimator · KITTI subsetRMSE_lin: 2.9100 -> 2.7998Improved
use freeform optimized lens on KITTI object detectionFrustum PointNet · KITTI object detection (val split)2D mAP: 78.01 -> 78.96No clear effect
use freeform optimized lens on KITTI object detectionFrustum PointNet · KITTI pedestrian 3D AP Moderate3D AP: 7.10 -> 11.74Improved
use freeform optimized lens on KITTI object detectionFrustum PointNet · KITTI cyclist 3D AP Moderate3D AP: 2.36 -> 4.89Improved
use freeform optimized lens for car 3D detectionFrustum PointNet · KITTI car 3D detection IoU 0.7 (val)AP Moderate: 13.82 -> 17.07Improved
use freeform optimized lens on cyclist 2D detectionFrustum PointNet · KITTI cyclist 2D AP2D AP: 89.77 -> 88.11Hurt

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