AI Paper Atlas

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

Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver

Xianpeng Liu, Ce Zheng, Kelvin B Cheng, Nan Xue, Guo-Jun Qi, Tianfu Wu

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 19 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 RoI appearance features for proposal verification (ablation)MonoXiver on MonoCon · KITTI val Car (Moderate)AP_3D: 19.01 -> 21.04Improved
add geometric embeddings (ablation)MonoXiver on MonoCon · KITTI val Car (Moderate)AP_3D: 21.04 -> 21.67Improved
use Perceiver instead of MLP to fuse appearance and geometry (ablation)MonoXiver on MonoCon · KITTI val Car (Moderate)AP_3D: 21.67 -> 22.40Improved
add rescoring head (ablation)MonoXiver on MonoCon · KITTI val Car (Moderate)AP_3D: 19.01 -> 21.41Improved
add localization residual branch (ablation)MonoXiver on MonoCon · KITTI val Car (Moderate)AP_3D: 21.41 -> 22.30Improved
add dimension residual branch (ablation)MonoXiver on MonoCon · KITTI val Car (Moderate)AP_3D: 22.30 -> 22.40Improved
apply MonoXiver to SMOKE backboneSMOKE · KITTI val Car (Moderate)AP_3D: 7.09 -> 9.40Improved
apply MonoXiver to MonoDLE backboneMonoDLE · KITTI val Car (Moderate)AP_3D: 13.72 -> 16.19Improved
apply MonoXiver to GUPNet and DEVIANTGUPNet, DEVIANT · Waymo val Level_1AP_3D: GUPNet 10.02 -> 11.47; DEVIANT 10.98 -> 11.88Improved
add MonoXiver second stage (inference cost)MonoCon · RTX5000 latencylatency (ms): 18 -> 25Hurt
use coarser sampling stride in oracle top-down grid (ablation)oracle local-grid search on MonoCon anchors · KITTI val Car (Moderate)AP_3D upper bound: 64.93 (stride 0.1, +-2) -> 34.44 (stride 0.75, +-1.5)Hurt

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