AI Paper Atlas

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

Reinforced Axial Refinement Network for Monocular 3D Object Detection

Lijie Liu, Chufan Wu, Jiwen Lu, Lingxi Xie, Jie Zhou, Qi Tian

ECCV 2020 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 26 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
use discrete refinement output instead of continuous regression (ablation)RAR-Net (MonoGRNet) · KITTI val 1, Easy, IoU=0.73D AP (%): 1.81 -> 18.25Improved
use parameter-aware image enhancement instead of simple fusion (ablation)RAR-Net (MonoGRNet) · KITTI val 1, Easy, IoU=0.73D AP (%): 0.40 -> 18.25Improved
use parameter-aware module instead of direct projection (ablation)RAR-Net (MonoGRNet) · KITTI val 1, Easy, IoU=0.73D AP (%): 10.88 -> 18.25Improved
use axial coordinate instead of world coordinate (ablation)RAR-Net (MonoGRNet) · KITTI val 1, Easy, IoU=0.73D AP (%): 5.34 -> 18.25Improved
output a single refinement operation (and use RL) instead of all at once (ablation)RAR-Net (MonoGRNet) · KITTI val 1, Easy, IoU=0.73D AP (%): 2.27 -> 18.25Improved
optimize with reinforcement learning (ablation)RAR-Net (MonoGRNet) · KITTI val 1, Easy, IoU=0.73D AP (%): 13.96 -> 18.25Improved
add RAR-Net refinementDeep3DBox · KITTI val 2, Easy, IoU=0.73D AP (%): 5.85 -> 14.25Improved
add RAR-Net refinementMonoGRNet · KITTI val 1, Easy, IoU=0.73D AP (%): 13.84 -> 18.25Improved
add RAR-Net refinementM3D-RPN · KITTI test, Easy3D AP (%): 14.76 -> 16.37Improved
add RAR-Net refinementD4LCN (uses depth data) · KITTI3D AP (%): +0.51% APImproved
add RAR-Net refinementDeep3DBox · KITTI val 2, EasyAOS (%): 98.59 -> 98.61No clear effect
add RAR-Net refinementDeep3DBox · KITTI bird's eye view val 2, Easy, IoU=0.7AP (%): 9.99 -> 14.38Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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