AI Paper Atlas

Research map / 3D vision / 3D generation

SceneScape: Text-Driven Consistent Scene Generation

NeurIPS 2023 · 3D vision › 3D generation · approach: Text-to-3D scene generation · 24 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 test-time depth finetuning (ablation)SceneScape · 20 videos, 10 promptsdepth SI-RMSEHelped
add test-time decoder finetuning (ablation)SceneScape · 20 videos, 10 promptsCOLMAP reprojection errorHelped
use unified mesh instead of 2D depth-aware splatting (ablation)SceneScape · 20 videos, 10 promptsCOLMAP metrics (pose, reprojection, SI-RMSE, completeness)Helped
use unified mesh instead of 2D splatting (ablation)SceneScape · AMT user studyuser preferenceHelped
add depth finetuning (ablation)SceneScape · AMT user studyuser preferenceNo clear effect
use SceneScape instead of VideoFusiontext-driven video generation · AMT visual quality% preference: 95.97Helped
use SceneScape instead of GEN-1text-driven video generation · AMT visual quality% preference: 69.34Helped
use SceneScape instead of GEN-1text-driven video generation · CLIP text similarityCLIP text-similarityNo 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