AI Paper Atlas

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

Kinematic 3D Object Detection in Monocular Video

Garrick Brazil, Gerard Pons-Moll, Xiaoming Liu, Bernt Schiele

ECCV 2020 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 194 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 orientation decomposition (axis, heading, offset) (ablation)baseline detector · KITTI val, Car IoU 0.7AP3D Moderate: 9.71 -> 12.10Improved
add self-balancing confidence loss (ablation)detector with orientation decomposition · KITTI val, Car IoU 0.7AP3D Moderate: 12.10 -> 12.77Improved
fuse self-balancing confidence with classification score (mu = c * omega) (ablation)detector with confidence loss · KITTI val, Car IoU 0.7AP3D Moderate: 12.77 -> 13.55Improved
add kinematic Kalman motion model over 4 frames (ablation)detector with decomposition and confidence · KITTI val, Car IoU 0.7AP3D Moderate: 13.55 -> 14.10Improved
use orientation decomposition instead of 10-bin classification (ablation)orientation head · KITTI val, Car IoU 0.7AP3D Moderate: 10.74 -> 12.10Improved
use orientation decomposition instead of 2-bin classification (ablation)orientation head · KITTI val, Car IoU 0.7AP3D Moderate: 9.47 -> 12.10Improved
use decomposed orientation instead of erratic baseline orientation inside the kinematic model (ablation)kinematic model · KITTI val, Car IoU 0.7AP3D Moderate: 11.47 -> 14.10Improved
keep orientation decomposition and uncertainty in the kinematic model (vs baseline orientation and constant mu) (ablation)kinematic model · KITTI val, Car IoU 0.7AP3D Moderate: 10.64 -> 14.10Improved
add orientation decomposition and kinematics (ablation)baseline detector · KITTI val, Car IoU 0.7mean angle error (deg): 13.4 -> 10.9 -> 6.1Improved
use mu = c * omega instead of classification score c (ablation)box rating · KITTI val, Car IoU 0.7correlation with 3D IoU: 0.301 -> 0.417Improved
forecast 1 frame ahead instead of current frame (ablation)kinematic Kalman model · KITTI val, Car IoU 0.7AP3D Moderate: 14.10 -> 10.64Hurt
forecast 2 frames ahead instead of current frame (ablation)kinematic Kalman model · KITTI val, Car IoU 0.7AP3D Moderate: 14.10 -> 5.10Hurt

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