AI Paper Atlas

Research map / 3D vision / 3D generation

UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer

Tianchen Deng, Chen Xun, Ziming Li, Hongming Shen, Shuhao Zhai, Danwei Wang, Javier Civera, Hesheng Wang

ECCV 2026 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 4 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 3D VGGT tokens to 2D tokens in the descriptor (ablation)UniPR-3D · Oxford2 sequence (2m)R@1: 75.9 -> 81.4Improved
add 2D patch tokens to 3D-only descriptor (ablation)UniPR-3D · MSLS valR@1: 91.9 -> 94.1Improved
use optimal transport instead of GeM for 3D patch tokens (ablation)UniPR-3D · Oxford2 sequence (2m)R@1: 78.8 -> 81.4Improved
add explicit 3D pose injection (ablation)UniPR-3D · Oxford2 sequence (2m)R@1: 81.4 -> 78.3Hurt
add 2D cls and register tokens (ablation)UniPR-3D · Oxford2 sequence (2m)R@1: 80.3 -> 81.4Improved
increase test-time sequence length from 5 to 15 frames (trained on 5) (ablation)UniPR-3D · Oxford2 sequence (2m)R@1: 80.6 -> 92.4Improved
reduce test-time sequence length from 5 to 3 frames (ablation)UniPR-3D · Oxford2 sequence (2m)R@1: 80.6 -> 70.3Hurt
replace DINOv2 single-view descriptor with VGGT 3D-token descriptor (single-frame)SALAD · single-frame VPR benchmarksR@1: SF-XL v1 95.3 (MegaLoc) vs 93.8 UniPR-3D; Nordland 76.0 -> 78.4Mixed
use UniPR-3D instead of CaseVPR for sequence retrieval (strict 2m)CaseVPR · Oxford2 sequence (2m)R@1: 72.8 -> 80.6Improved
use VGGT backbone instead of DINOv2 backbone, latencyCaseVPR · Oxford1latency: 75 -> 140Hurt

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