Fast 3D Indoor Scene Synthesis with Discrete and Exact Layout Pattern Extraction

Abstract

We present a fast framework for indoor scene synthesis, given a room geometry and a list of objects with learnt priors. Unlike existing data-driven solutions, which often extract priors by co-occurrence analysis and statistical model fitting, our method measures the strengths of spatial relations by tests for complete spatial randomness (CSR), and extracts complex priors based on samples with the ability to accurately represent discrete layout patterns. With the extracted priors, our method achieves both acceleration and plausibility by partitioning input objects into disjoint groups, followed by layout optimization based on the Hausdorff metric. Extensive experiments show that our framework is capable of measuring more reasonable relations among objects and simultaneously generating varied arrangements in seconds.

We currently received our first valuable comments from reviewers. We will continuing modify our paper accordingly, so this paper will be modified frequently

References in corpus (7)

• InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset
• 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions
• Fast and Scalable Position-Based Layout Synthesis
• Text to 3D Scene Generation with Rich Lexical Grounding
• Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling
• Scan2CAD: Learning CAD Model Alignment in RGB-D Scans
• Automatic Generation of Constrained Furniture Layouts

Cited by in corpus (3)

• ATISS: Autoregressive Transformers for Indoor Scene Synthesis
• SceneGen: Generative Contextual Scene Augmentation using Scene Graph Priors
• Static and Animated 3D Scene Generation from Free-form Text Descriptions