AI Paper Atlas

Research map / 3D vision / 3D generation

Where am I? Scene Retrieval with Language

Jiaqi Chen, Daniel Barath, Iro Armeni, Marc Pollefeys, Hermann Blum

ECCV 2024 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 12 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
score matches by embedding cosine similarity instead of matching probability (ablation)Text2SGM · ScanScribe (top-1 of 10)recall: 63.70 -> 68.27Improved
precompute scene graph embeddings with a fixed paired input (retrieval-based matching) (ablation)Text2SGM · ScanScribe (top-1 of 10)recall: 68.27 -> 68.61No clear effect
train with both cosine similarity and matching probability losses instead of cosine only (ablation)Text2SGM · Human (top-1 of 10)recall: 44.88 -> 51.38Improved
train with both losses instead of cosine only (ablation)Text2SGM · ScanScribe (top-1 of 10)recall: 65.17 -> 62.70No clear effect
use more self/cross-attention modules (N=1 to N=4) (ablation)Text2SGM · ScanScribe (top-1 of 10)recall: 62.70 -> 23.02Hurt
use more self/cross-attention modules (N=1 to N=2) (ablation)Text2SGM · Human (top-1 of 10)recall: 51.38 -> 45.05Hurt
use Text2SGM scene graph embeddings instead of CLIP image embeddings on open-set human queries (top-5 of 10)Text2SGM · Human (top-5 of 10)recall: 95.11 (CLIP2CLIP) vs 94.87Mixed
use scene graphs and text-graphs instead of CLIP on ScanScribeText2SGM · ScanScribe (top-1 of 10)recall: 33.09 -> 68.27Improved
use point-cloud based Text2Pos coarse localization indoorsText2Pos · ScanScribe, 55 scenes (top-5 of all)recall: 10.27 vs 76.34 for Text2SGMHurt
evaluate with GPT-4 queries generated from images (biased toward CLIP)Text2SGM · ScanScribe (top-1 of 10)recall: 33.07 -> 34.22No clear effect

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