AI Paper Atlas

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

Scene Reconstruction as Mapping Priors for 3D Detection

Yang Fu, Yuliang Zou, Hao Xiang, Xin Huang, Yijing Bai, Chen Song, Weijing Shi, Govind Thattai, Dragomir Anguelov, Mingxing Tan, Yingwei Li

CVPR 2026 · Detection and segmentation › 3D detection and driving · approach: 3D objectness and scene segmentation · 0 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 surfel and 3DGS mapping priors (ablation)Ours-baseline · WOD validation subsetOverall L2 APH: 80.1 -> 81.7Improved
add surfel and 3DGS mapping priors (ablation)SWFormer-dagger · WOD validation subsetOverall L2 APH: 71.6 -> 72.7Improved
add surfel prior only (ablation)Ours-baseline · WOD validation subsetOverall L2 APH: 80.1 -> 81.1Improved
add 3DGS prior only (ablation)Ours-baseline · WOD validation subsetOverall L2 APH: 80.1 -> 81.0Improved
add surfel or 3DGS prior to weaker baseline (ablation)SWFormer-dagger · WOD validation subsetPedestrian L2 AP: 73.8 -> 73.5Hurt
use gated fusion instead of concatenation (ablation)MPA3D fusion · WOD validation subsetOverall L2 AP: 80.4 -> 83.3Improved
use gated fusion instead of averaging (ablation)MPA3D fusion · WOD validation subsetOverall L2 APH: 77.0 -> 81.7Improved
use gated fusion instead of sum (ablation)MPA3D fusion · WOD validation subsetOverall L2 APH: 73.4 -> 81.7Improved
add camera input to LiDAR (ablation)MPA3D-96M · WOD validationOverall L2 APH: 74.9 -> 75.7Improved
add surfel prior to LiDAR+camera (ablation)MPA3D-96M · WOD validationOverall L2 APH: 75.7 -> 76.1Improved
add 3DGS prior to LiDAR+camera+surfel (ablation)MPA3D-96M · WOD validationOverall L2 APH: 76.1 -> 77.4Improved
use mapping priors with 4 frames instead of 100-frame temporal fusionMPA3D vs MAD · WOD test leaderboardOverall L2 APH: 80.2 -> 81.6Improved

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