AI Paper Atlas

Research map / 3D vision / 3D generation

SceneTeller: Language-to-3D Scene Generation

Basak Melis Ocal, Maxim Tatarchenko, Sezer Karaoglu, Theo Gevers

ECCV 2024 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 41 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
select in-context exemplars by retrieval instead of randomly (ablation)SceneTeller layout generation (R+GPT) · 3D-FRONT layoutsmIoU (%): 29.90 -> 44.20Improved
select in-context exemplars by retrieval instead of randomly (ablation)SceneTeller layout generation (R+GPT) · 3D-FRONT layoutsOOB rate (%): 76.11 -> 54.65Improved
add GPT paraphrasing to rule-based prompts with retrieval exemplars (ablation)SceneTeller layout generation · 3D-FRONT layoutsOOB rate (%): 64.87 -> 54.65Improved
add GPT paraphrasing to rule-based prompts with retrieval exemplars (ablation)SceneTeller layout generation · 3D-FRONT layoutsmIoU (%): 45.50 -> 44.20No clear effect
add negative exemplars (pos+neg) in place of all retrieved exemplars (ablation)SceneTeller layout generation · 3D-FRONT layoutsmIoU (%): 31.10 -> 41.90 vs random; 45.50 retrievalMixed
use GPT-4 in-context layout generation instead of human drawinglayout generation · 3D-FRONT layoutsmIoU (%): 28.70 -> 44.60Improved
use GPT-4 in-context layout generation instead of human drawinglayout generation · 3D-FRONT layoutsOOB rate (%): 12.09 -> 56.78Hurt
generate layout first then assemble and stylize with 3DGS versus baseline scene generatorsSceneTeller · ScanNet FIDFID: 238.75 -> 167.27Improved

Later papers that compared with this method

2 later accepted papers report SceneTeller as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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