AI Paper Atlas

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

Pixel-Aligned Recurrent Queries for Multi-View 3D Object Detection

Yiming Xie, Huaizu Jiang, Georgia Gkioxari, Julian Straub

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 11 citations (OpenAlex)

This paper tried a common change: Add positional encoding

add ray positional encodings to image features · ScanNet · F1 @IoU>0.5: 28.2 -> 30.0 Improved

What 646 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 pixel-aligned appearance features to queries (ablation)PARQ · ScanNetF1 @IoU>0.5: 27.1 -> 30.0Improved
add recurrent refinement of 3D reference points (ablation)PARQ · ScanNetF1 @IoU>0.5: 27.6 -> 30.0Improved
include positional encoding of 3D reference point in query (ablation)PARQ · ScanNetF1 @IoU>0.5: 10.4 -> 30.0Improved
add ray positional encodings to image features (ablation)PARQ · ScanNetF1 @IoU>0.5: 28.2 -> 30.0Improved
use more views at inference than training (3)PARQ · ScanNetF1 @IoU>0.5: 30.0 -> 31.3 (7 views)Improved
use more views at inference than training (3)PETR and ImVoxelNet · ScanNetF1 @IoU>0.5: PETR 25.6 -> 24.4 (7 views); ImVoxelNet 26.8 -> 23.3 (9 views)No clear effect
reduce queries to 32 and iterations to 2 at inferencePARQ · ScanNetinference time and F1: 290 ms -> 105 ms; F1 30.0 -> 28.2 at IoU>0.5Mixed
use PARQ rather than ImVoxelNet at loose IoU thresholdScanNet IoU>0.25 · ScanNetF1: 51.7 -> 51.1Hurt
use PARQ instead of PETR on ARKitScenesmulti-view 3D detection · ARKitScenes IoU>0.5F1: 17.5 -> 24.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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