AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs

Yang Miao, Francis Engelmann, Olga Vysotska, Federico Tombari, Marc Pollefeys, Daniel Barath

ECCV 2024 · Vision-language and multimodal › Human and embodied modeling · approach: Region-level vision-language alignment · 20 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
use SceneGraphLoc scene-graph embeddings instead of LidarCLIP / LIP-Loc point-cloud global descriptorscross-modal coarse localization · 3RScan test, 50 scenes, staticRecall@1: 4.7 (LidarCLIP) -> 30.2Improved
add images to the scene graph map embeddings (ablation)SceneGraphLoc · 3RScan test, 50 scenes, temporalRecall@1: 28.2 -> 69.3Improved
add attributes to point cloud map modality (ablation)SceneGraphLoc · 3RScan val (temporal)Recall@1: 43.9 -> 54.8Improved
add relationships modality (ablation)SceneGraphLoc · 3RScan val (temporal)Recall@1: 56.5 -> 62.7Improved
add structure modality on top of point cloud and attributes (ablation)SceneGraphLoc · 3RScan val (temporal)Recall@1: 54.8 -> 56.5Improved
add attributes, structure, relationships to point cloud plus images (ablation)SceneGraphLoc with GCViT features · 3RScan val (temporal)Recall@1: 73.2 -> 72.1No clear effect
use DINOv2 instead of GCViT image features (ablation)SceneGraphLoc · 3RScan val (temporal)Recall@1: 72.1 -> 88.5Improved
increase number of views per object beyond 10 (ablation)image modality embedding · 3RScan val (temporal)Recall@1: 88.5 (10 views) -> 86.3 (15) / 86.8 (20)No clear effect
use transformer encoder with pose positional encoding and max-pooling for multi-view fusion (ablation)image modality embedding · 3RScan val (temporal)Recall@1: 85.5 -> 88.5Improved
use SceneGraphLoc without images versus OpenMask3D on ScanNet all scenesscene graph map without images · ScanNet test (all 210 scenes)Recall@1: 16.5 (OpenMask3D) vs 13.5Hurt

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