3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics

Abstract

We introduce 3D-FRONT (3D Furnished Rooms with layOuts and semaNTics), a new, large-scale, and comprehensive repository of synthetic indoor scenes highlighted by professionally designed layouts and a large number of rooms populated by high-quality textured 3D models with style compatibility. From layout semantics down to texture details of individual objects, our dataset is freely available to the academic community and beyond. Currently, 3D-FRONT contains 18,968 rooms diversely furnished by 3D objects, far surpassing all publicly available scene datasets. In addition, the 13,151 furniture objects all come with high-quality textures. While the floorplans and layout designs are directly sourced from professional creations, the interior designs in terms of furniture styles, color, and textures have been carefully curated based on a recommender system we develop to attain consistent styles as expert designs. Furthermore, we release Trescope, a light-weight rendering tool, to support benchmark rendering of 2D images and annotations from 3D-FRONT. We demonstrate two applications, interior scene synthesis and texture synthesis, that are especially tailored to the strengths of our new dataset. The project page is at: https://tianchi.aliyun.com/specials/promotion/alibaba-3d-scene-dataset.

Project page: https://tianchi.aliyun.com/specials/promotion/alibaba-3d-scene-dataset

References in corpus (9)

• Semi-Supervised Classification with Graph Convolutional Networks
• Joint 2D-3D-Semantic Data for Indoor Scene Understanding
• Learning Representations and Generative Models for 3D Point Clouds
• The Replica Dataset: A Digital Replica of Indoor Spaces
• InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset
• Fast and Scalable Position-Based Layout Synthesis
• 3D-FUTURE: 3D Furniture shape with TextURE
• OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets
• TM-NET: Deep Generative Networks for Textured Meshes

Cited by in corpus (9)

• iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenes
• Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI
• Panoptic 3D Scene Reconstruction From a Single RGB Image
• FlairGPT: Repurposing LLMs for Interior Designs
• LUMINOUS: Indoor Scene Generation for Embodied AI Challenges
• Roominoes: Generating Novel 3D Floor Plans From Existing 3D Rooms
• LayoutGMN: Neural Graph Matching for Structural Layout Similarity
• Reconstructing Interactive 3D Scenes by Panoptic Mapping and CAD Model Alignments
• MINERVAS: Massive INterior EnviRonments VirtuAl Synthesis