AI Paper Atlas

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

Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery

Greire Payen de La Garanderie, Amir Atapour Abarghouei, Toby P. Breckon

ECCV 2018 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 3 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 projection transformation to training data (ablation)3D detector · CARLA panoramicmAP: 0.336 -> 0.244Hurt
add style transfer from Mapillary and CARLA combined (ablation)3D detector · CARLA panoramicmAP: 0.336 -> 0.378Improved
add style transfer from CARLA only (ablation)3D detector · CARLA panoramicmAP: 0.336 -> 0.355Improved
add style transfer from Mapillary only (ablation)3D detector · CARLA panoramicmAP: 0.336 -> 0.359Improved
add projection transformation to style M+C training data (ablation)3D detector · CARLA panoramicmAP: 0.378 -> 0.344Hurt
add projection transformation to training data for depth (ablation)Monocular depth · CARLA panoramic depthdelta<1.25 accuracy: 0.697 -> 0.732Improved
add style transfer from CARLA to depth training data (ablation)Monocular depth · CARLA panoramic depthdelta<1.25 accuracy: 0.697 -> 0.686Hurt
add style transfer from Mapillary and CARLA to depth training data (ablation)Monocular depth · CARLA panoramic depthAbs. rel.: 0.247 -> 0.230Improved
add projection transformation on top of style C for depth (ablation)Monocular depth · CARLA panoramic depthAbs. rel.: 0.262 -> 0.292Hurt
train detector on CARLA-adapted data, test on real CARLA instead of adapted images3D detector · CARLA panoramicmAP: 0.82 -> 0.35Hurt
replace zero-padding with horizontal ring-padding (ablation)Panoramic detector and depth network · Mapillary panoramas (qualitative)boundary detection and depth continuityImproved

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