AI Paper Atlas

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

Learning Object-Specific Distance From a Monocular Image

Jing Zhu, Yi Fang

ICCV 2019 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 88 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 multiclass classifier (ablation)base model (vgg16) · KITTI-distancedelta1 accuracy: 0.482 -> 0.587Improved
add multiclass classifier (ablation)base model (vgg16) · KITTI-distanceAbs Rel: 0.658 -> 0.311Improved
add multiclass classifier (ablation)enhanced model (vgg16) · KITTI-distancedelta1 accuracy: 0.486 -> 0.629Improved
add multiclass classifier (ablation)enhanced model (vgg16) · KITTI-distanceAbs Rel: 0.541 -> 0.251Improved
add keypoint regressor and projection lossbase model (vgg16) · KITTI-distance (average)delta1 accuracy: 0.587 -> 0.629Improved
add keypoint regressor and projection lossbase model (vgg16) · KITTI-distance (average)Abs Rel: 0.311 -> 0.251Improved
add keypoint regressor and projection lossbase model (res50) · KITTI-distance (average)delta1 accuracy: 0.503 -> 0.550Improved
add keypoint regressor and projection lossbase model (vgg16) · nuScenes (mini) distancedelta1 accuracy: 0.393 -> 0.535Improved
add keypoint regressor and projection lossbase model (res50) · nuScenes (mini) distanceAbs Rel: 0.466 -> 0.340Improved
use learned base model instead of IPMIPM · KITTI-distance (average)Abs Rel: 0.390 -> 0.311Improved
use VGG16 instead of ResNet50 backbonebase model · KITTI-distance (average)delta1 accuracy: 0.503 -> 0.587Improved
use learned enhanced model instead of IPMIPM · nuScenes (mini) distancedelta1 accuracy: 0.441 -> 0.535Improved

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