FurniScene: A Large-scale 3D Room Dataset with Intricate Furnishing Scenes
Indoor scene generation has attracted significant attention recently as it is crucial for applications of gaming, virtual reality, and interior design. Current indoor scene generation methods can produce reasonable room layouts but often lack diversity and realism. This is primarily due to the limited coverage of existing datasets, including only large furniture without tiny furnishings in daily life. To address these challenges, we propose FurniScene, a large-scale 3D room dataset with intricate furnishing scenes from interior design professionals. Specifically, the FurniScene consists of 11,698 rooms and 39,691 unique furniture CAD models with 89 different types, covering things from large beds to small teacups on the coffee table. To better suit fine-grained indoor scene layout generation, we introduce a novel Two-Stage Diffusion Scene Model (TSDSM) and conduct an evaluation benchmark for various indoor scene generation based on FurniScene. Quantitative and qualitative evaluations demonstrate the capability of our method to generate highly realistic indoor scenes. Our dataset and code will be publicly available soon.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityLayout GenerationScene GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Agents' Room: Narrative Generation through Multi-step Collaboration
Writing compelling fiction is a multifaceted process combining elements such as crafting a plot, developing interesting characters, and using evocative language. While large language models (LLMs) show promise for story …
Orchestrating Spatial Semantics via a Zone-Graph Paradigm for Intricate Indoor Scene Generation
Autonomous 3D indoor scene synthesis breaks down in non-convex rooms with tightly coupled spatial constraints. Data-driven generators lack topological priors for long-horizon planning, while iterative agents fragment sem…
Indoor Scene SynthesisScene GenerationHouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild
Current 3D layout estimation models are primarily trained on synthetic datasets containing simple single room or single floor environments. As a consequence, they cannot natively handle large multi floor buildings and re…
Scene UnderstandingRealClass: A Framework for Classroom Speech Simulation with Public Datasets and Game Engines
The scarcity of large-scale classroom speech data has hindered the development of AI-driven speech models for education. Classroom datasets remain limited and not publicly available, and the absence of dedicated classroo…
Data AugmentationSimClass: A Classroom Speech Dataset Generated via Game Engine Simulation For Automatic Speech Recognition Research
The scarcity of large-scale classroom speech data has hindered the development of AI-driven speech models for education. Public classroom datasets remain limited, and the lack of a dedicated classroom noise corpus preven…
Automatic Speech RecognitionData AugmentationRobust Speech Recognitionspeech-recognition+1