AI Paper Atlas

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

Monocular 3D Object Detection with Depth from Motion

Tai Wang, Jiangmiao Pang, Dahua Lin

ECCV 2022 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 68 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 flip augmentation (ablation)DfM stereo cost volume baseline · KITTI val carAP3D Moderate: 12.93 -> 13.92Improved
add rescale augmentation (ablation)DfM stereo cost volume baseline · KITTI val carAP3D Moderate: 13.92 -> 15.32Improved
add monocular compensation to stereo-only depth (ablation)DfM · KITTI val carAP3D Moderate: 15.32 -> 18.82Improved
add stereo branch to mono-only (ablation)DfM · KITTI val carAP3D Moderate: 15.30 -> 18.82Improved
add stereo to mono at hard level (ablation)DfM · KITTI val carAP3D Hard: 14.05 -> 16.47Mixed
use later preceding frame (1st to 3rd) at inference (ablation)DfM · KITTI val carAP3D Moderate: 17.27 -> 17.62 -> 17.96Improved
use quaternion rotation instead of Euler (ablation)pose-free DfM · KITTI val carAP3D Moderate: 15.03 -> 16.93Improved
add reprojection photometric supervision (ablation)pose-free DfM · KITTI val carAP3D Moderate: 16.93 -> 18.49Improved
use group-wise fusion instead of shared-weight monocular branch (ablation)DfM · KITTI val carAP3D Moderate: 15.99 -> 16.52Improved
use point-wise fusion instead of group-wise fusion (ablation)DfM · KITTI val carAP3D Moderate: 16.52 -> 18.82Improved
replace CE with focal loss (gamma=2) for depth (ablation)DfM · KITTI val carAP3D Moderate: 18.82 -> 18.76No clear effect
add foreground-balanced weights to depth loss (ablation)DfM · KITTI val carAP3D Moderate: 18.82 -> 19.11Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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