AI Paper Atlas

Research map / 3D vision / 3D generation

Scene Generation at Absolute Scale: Utilizing Semantic and Geometric Guidance From Text for Accurate and Interpretable 3D Indoor Scene Generation

Stefan Ainetter, Thomas Deixelberger, Edoardo Dominici, Philipp Drescher, Konstantinos Vardis, Markus Steinberger

ECCV 2026 · 3D vision › 3D generation · approach: Text-to-3D scene generation · 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 Multi-ControlNet (depth + semantic) conditioning (ablation)panorama generator · Structured3D panoramasCLIP Score: 31.17 -> 32.48Improved
add Multi-ControlNet (depth + semantic) conditioning (ablation)panorama generator · Structured3D panoramasQ-Align: 4.45 -> 4.54Improved
add depth ControlNet alone (ablation)panorama generator · Structured3D panoramasCLIP Score: 31.17 -> 31.85Improved
add semantic ControlNet alone (ablation)panorama generator · Structured3D panoramasCLIP Score: 31.17 -> 32.23Improved
add semantic ControlNet alone (ablation)panorama generator · Structured3D panoramasIS: 3.33 -> 3.41Improved
add depth and semantic ControlNets together vs semantic only (ablation)panorama generator · Structured3D panoramasIS: 3.41 -> 3.26Hurt
use optimized collision-aware overlapping trajectories instead of coverage-maximizing view planning (ablation)trajectory sampling · Structured3D promptsMEt3R: 0.029 -> 0.024Improved
add depth filter to standard view planning (ablation)trajectory sampling · Structured3D promptsMEt3R: 0.029 -> 0.027Improved
add depth-guided camera scale alignment (ablation)Stable Virtual Camera trajectories · Structured3D promptscamera pose alignmentImproved
replace WorldExplorer exhaustive trajectories with optimized samplingGuidedSceneGen · Structured3D promptsruntime per scene: 7h -> 0.75hImproved
use GuidedSceneGen instead of DreamScene3603D scene generation · Structured3D promptsMEt3R: 0.026 -> 0.024Improved
use GuidedSceneGen instead of WorldExplorer3D scene generation · Structured3D promptsIS: 2.27 -> 2.22Hurt

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