PulseTrendingJournal ClubResearchersJournalsExplore
Instagram
HomeTrendingJournal ClubExplore
Synapse
⌘+K
Synapse
September 10, 2025IEEE Transactions on Pattern Analysis and Machine Intelligence

Planner3D: LLM-enhanced Graph Prior Meets 3D Indoor Scene Explicit Regularization

View Full Paper
Ask AI
Bookmark
Share

Authors

YWYao WeiMMMartin Renqiang MinGVGeorge Vosselman

Discussion

Loading...

Member takes

Overview

Generative model improves 3D indoor scene fidelity in spatial arrangements, indicating a new approach to scene graph integration.

Key Points

  • The proposed method achieves better scene-level fidelity in 3D indoor scene synthesis, enhancing realism and layout accuracy.
  • Benchmarked on the SG-FRONT dataset, the approach shows significant improvements in generating coherent indoor environments.
  • Utilizing a large language model, the study integrates global and local graph features to optimize layout-shape generation.
  • The introduction of explicit regularization in 3D layouts addresses layout collisions effectively, showcasing innovative constraints.

Cite This Study

Wei et al. (2025) studied this question.

synapsesocial.com/papers/68c1d22854b1d3bfb60f76a1https://doi.org/10.1109/tpami.2025.3602216
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. 1Planner3D: LLM-enhanced graph prior meets 3D indoor scene explicit regularization2024
  2. 2OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization2025
  3. 3GeoSceneGraph: Geometric Scene Graph Diffusion Model for Text-guided 3D Indoor Scene Synthesis2026 · 1 citations
  4. 4CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling2026
  5. 5InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis With Semantic Graph Prior2025 · 1 citations