AI Paper Atlas

Research map / 3D vision / Depth and stereo

PGGT-Loc: Primitive-Grounded Geometry Transformer for Feed-Forward Camera Localization

Hanqiao Ye, Yuzhou Liu, Mengqi Rong, Jian Liu, Yangdong Liu, Shuhan Shen

NeurIPS 2026 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes PGGT-Loc, a primitive-grounded geometry transformer for feed-forward camera localization that uses compact scene primitives from readily available structured maps instead of dedicated costly maps.

Problem

Camera localization typically relies on multi-stage pipelines and dedicated maps that are costly to construct, store, and maintain, while well-structured primitive-based maps that are often available have not been exploited for direct camera localization.

Approach

Uses compact, interpretable scene primitives from existing structured maps as the localization reference, grounding a geometry transformer in these primitives to regress camera pose feed-forward rather than through a multi-stage pipeline.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add patch-primitive assignment loss (ablation)PGGT-Loc (Ray) · ScanNetpose recall (fine threshold, %): 54.7 -> 62.0Improved
add primitive parameter loss (ablation)PGGT-Loc (Ray) · ScanNetpose recall (fine threshold, %): 54.9 -> 62.0Improved
add prepended camera/map token pose loss (ablation)PGGT-Loc (Ray) · ScanNetpose recall (fine threshold, %): 59.7 -> 62.0Mixed
add semantics injection alone (ablation)PGGT-Loc layout · S3D-resampled 90 deg FoV1 m median translation error (cm): 15.2 -> 17.3Hurt
add room isolation attention mask alone (ablation)PGGT-Loc layout · S3D-resampled 90 deg FoVpose recall at 1 m (%): 90.5 -> 93.8Improved
add semantics and isolation jointly (ablation)PGGT-Loc layout · S3D-resampled 90 deg FoVpose recall at 1 m (%): 90.5 -> 95.5Improved
use full multi-task supervision instead of ray loss only (ablation)PGGT-Loc (Ray) · ScanNetpose recall (fine threshold, %): 51.7 -> 62.0Improved
derive pose from ray map instead of plane parameters (ablation)PGGT-Loc · ScanNetpose recall (fine threshold, %): 59.5 -> 69.0Improved
derive pose from ray map instead of plane parameters (ablation)PGGT-Loc layout · S3D-officialpose recall at 1 m (%): 76.7 -> 93.6Improved
use camera token instead of ray map (ablation)PGGT-Loc · ScanNetpose recall (fine threshold, %): 69.0 -> 68.9No clear effect
remove plane parameter inputs and prediction (ablation)PGGT-Loc · ScanNetcoarse recallNo clear effect
feed-forward grounding instead of render-and-comparePGGT-Loc vs SPVLoc · S3D-officialpose recall at 1 m (%): 84.5 -> 93.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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