PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
October 20, 20250 citationsOpen Access

M3DLayout: A Comprehensive Multi-Source Dataset for 3D Indoor Layout Generation

M3DLayout: A Multi-Source Dataset of 3D Indoor Layouts and Structured Descriptions for 3D Generation

View Full Paper
Ask AI
Bookmark
Share

Authors

YZYiheng ZhangZCZhuojiang CaiMWMingdao Wang

Discussion

Loading...

Member takes

Overview

Introducing M3DLayout that enhances 3D indoor layout generation through diverse datasets and semantic control.

Key Points

  • M3DLayout comprises 15,080 layouts and over 258k object instances to improve 3D generation.
  • The dataset integrates real-world scans, CAD designs, and procedurally generated scenes for diversity.
  • It includes detailed structured descriptions for both global scene summaries and item placements.
  • The benchmark created with a text-conditioned model shows M3DLayout supports advanced layout generation.

Cite This Study

Zhang et al. (2025) studied this question.

synapsesocial.com/papers/68f6379bb481a140a36cf4ddhttps://doi.org/10.48550/arxiv.2509.23728
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1IL3D: A Large-Scale Indoor Layout Dataset for LLM-Driven 3D Scene Generation2025
  2. 2OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization2025
  3. 3CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling2026
  4. 4Planner3D: LLM-enhanced Graph Prior Meets 3D Indoor Scene Explicit Regularization2025 · 5 citations
  5. 5LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Model2024 · 1 citations