AI Paper Atlas

Research map / 3D vision / 3D generation

LangLoc: “Tell Me What You See”

Shaurya Kishore Panwar, Roham Zendehdel Nobari, Shirley Lau, Abu Bakr Rahman Shaik, Manuel Günther, Marc Pollefeys, Daniel Barath

ECCV 2026 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 0 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 Bayesian yes/no dialog (ablation)LangLoc · 3RScan (100 scenes)median position error (m): 1.55 -> 0.80Improved
add Bayesian yes/no dialog (ablation)LangLoc · 3RScan (100 scenes)mean angular error (deg): 46.1 -> 39.5Improved
add Bayesian yes/no dialog (ablation)LangLoc · 3RScan (100 scenes)3D IoU: 0.172 -> 0.342Improved
add Bayesian yes/no dialog (ablation)LangLoc · ScanNet (100 scenes)median position error (m): 1.31 -> 0.07Improved
add Bayesian yes/no dialog (ablation)LangLoc · ScanNet (100 scenes)median angular error (deg): 34.7 -> 5.1Improved
add Bayesian yes/no dialog (ablation)LangLoc · ScanNet (100 scenes)3D IoU: 0.236 -> 0.593Improved
add human-typed dialog answers (ablation)LangLoc · Human dialog pilot (10 scenes)mean position error (m): 1.74 -> 0.66Improved
use ray-cast visibility scoring instead of zero-shot Qwen2.5-VL-2BLangLoc · 3RScan (100 scenes)mean angular error (deg): 85.5 -> 46.1Improved
use LangLoc without dialog instead of floor-centroid midpointLangLoc w/o dialog · 3RScan (100 scenes)mean position error (m): 1.416 -> 1.712Hurt
use LangLoc dual-branch GATv2 retrieval instead of Text2SGM (ret-based)LangLoc · ScanScribe retrieval (10-scene pool)Top-1 recall (%): 68.61 -> 76.70Improved
use LangLoc instead of Text2SGM (cos-sim) on full 55-scene poolLangLoc · ScanScribe retrieval (55-scene pool)Top-5 recall (%): 76.34 -> 83.30Improved
use LangLoc instead of Text2SGM under LLM-generated queriesLangLoc · ScanScribe retrieval (LLM-generated queries)Top-1 recall (%): 34.22 -> 59.5Improved

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