AI Paper Atlas

Research map / 3D vision / 3D generation

EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries

Jinjie Mai, Abdullah Hamdi, Silvio Giancola, Chen Zhao, Bernard Ghanem

ICCV 2023 · 3D vision › 3D generation · approach: Monocular 3D object reconstruction · 24 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
replace Matterport re-localization with COLMAP egocentric SfM for camera poses (ablation)Ego4D VQ3D baseline · Ego4D VQ3D testSuccess rate (%): 8.71 -> 77.27Improved
use detection peaks instead of last tracking response (ablation)EgoLoc · Ego4D VQ3D validationSuccess rate (%): 73.78 -> 78.05Improved
use multiple detection peaks instead of last peak (ablation)EgoLoc · Ego4D VQ3D validationSuccess rate (%): 78.05 -> 80.49Improved
weight multi-view 3D predictions by detection confidence instead of simple mean (ablation)EgoLoc · Ego4D VQ3D validationSuccess rate (%): 79.88 -> 80.49Improved
weighted multi-view aggregation on test server (ablation)EgoLoc · Ego4D VQ3D testSuccess rate (%): 86.36 -> 87.12Improved
use ground-truth 2D tracking instead of detected peaks (ablation)EgoLoc · Ego4D VQ3D validationSuccess* (%): 97.39 -> 98.04/98.69No clear effect
replace DPT monocular depth with multi-view triangulation (ablation)EgoLoc · Ego4D VQ3D validationSuccess rate (%): 80.49 -> 56.1Hurt
replace DPT depth with random depth (ablation)EgoLoc · Ego4D VQ3D validationSuccess rate (%): 80.49 -> 34.15Hurt
add Gaussian noise to DPT depth scale and shift (ablation)EgoLoc · Ego4D VQ3D validationSuccess rate (%): 80.49 -> 78.66Hurt

Later papers that compared with this method

2 later accepted papers report EgoLoc-v1 as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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