Text to 3D Scene Generation with Rich Lexical Grounding

Abstract

The ability to map descriptions of scenes to 3D geometric representations has many applications in areas such as art, education, and robotics. However, prior work on the text to 3D scene generation task has used manually specified object categories and language that identifies them. We introduce a dataset of 3D scenes annotated with natural language descriptions and learn from this data how to ground textual descriptions to physical objects. Our method successfully grounds a variety of lexical terms to concrete referents, and we show quantitatively that our method improves 3D scene generation over previous work using purely rule-based methods. We evaluate the fidelity and plausibility of 3D scenes generated with our grounding approach through human judgments. To ease evaluation on this task, we also introduce an automated metric that strongly correlates with human judgments.

10 pages, 7 figures, 3 tables. To appear in ACL-IJCNLP 2015

References in corpus (2)

• Grounded Semantic Composition for Visual Scenes
• A Joint Model of Language and Perception for Grounded Attribute Learning

Cited by in corpus (6)

• VoxML: A Visualization Modeling Language
• Fast 3D Indoor Scene Synthesis with Discrete and Exact Layout Pattern Extraction
• Geometry-Based Layout Generation with Hyper-Relations AMONG Objects
• End-to-End Optimization of Scene Layout
• Multimodal Semantic Simulations of Linguistically Underspecified Motion Events
• Grounding 'Grounding' in NLP