Pith. sign in

REVIEW 18 cited by

InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.04717 v1 pith:VYEQI47W submitted 2024-02-07 cs.CV

Chenguo Lin , Yadong Mu This is my paper · ORCID
classification cs.CV
keywords scenesynthesisgraphinstructscenepriorsemanticcontrollabilitydistributions
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Comprehending natural language instructions is a charming property for 3D indoor scene synthesis systems. Existing methods directly model object joint distributions and express object relations implicitly within a scene, thereby hindering the controllability of generation. We introduce InstructScene, a novel generative framework that integrates a semantic graph prior and a layout decoder to improve controllability and fidelity for 3D scene synthesis. The proposed semantic graph prior jointly learns scene appearances and layout distributions, exhibiting versatility across various downstream tasks in a zero-shot manner. To facilitate the benchmarking for text-driven 3D scene synthesis, we curate a high-quality dataset of scene-instruction pairs with large language and multimodal models. Extensive experimental results reveal that the proposed method surpasses existing state-of-the-art approaches by a large margin. Thorough ablation studies confirm the efficacy of crucial design components. Project page: https://chenguolin.github.io/projects/InstructScene.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 18 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. D3D-GEN: Robot-Aware Domain-Grounded Interactive 3D World Generation for Social Robotics

    cs.RO 2026-08 conditional novelty 6.0 of 10

    D3D-GEN automatically builds a domain knowledge base from web research and uses it to generate interactive 3D robot simulation worlds for residential, office, and hospital settings.

  2. Agentic Designer: Progressive Multi-Agent Collaboration for Structure-Aware Interior Layout Generation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A progressive generator-evaluator-refiner loop, trained on a new 18,853-room benchmark, reduces furniture-boundary violations in generated interior layouts from more than 90% to single digits while keeping layout density.

  3. CR-Refiner: An Object-Centric Optimal Transport Reranker for Edit-Conditioned 3D Scene Retrieval

    cs.CV 2026-07 conditional novelty 6.0 of 10

    An unbalanced optimal-transport reranker with structural priors and an LLM verifier improves hard-subset 3D scene retrieval, evaluated on the new synthetic 3D-CER benchmark.

  4. SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion

    cs.CV 2026-07 conditional novelty 6.0 of 10

    SynCity 3000 generates large, coherent 3D scenes from text by fine-tuning an image-to-3D diffusion model to operate convolutionally on overlapping windows, trained on procedurally generated synthetic scene data.

  5. 3D-Generalist: Self-Improving Vision-Language-Action Models for Crafting 3D Worlds

    cs.GR 2025-07 conditional novelty 6.0 of 10

    A self-improving vision-language-model policy iteratively crafts 3D environments from text, and renderings of those environments serve as effective synthetic pretraining data for vision models.

  6. PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

    cs.CV 2025-06 conditional novelty 6.0 of 10

    PartCrafter generates several separable 3D part meshes at once from a single image by fine-tuning a pretrained 3D diffusion transformer with part identity tokens and local-global attention.

  7. FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts

    cs.CV 2025-06 conditional novelty 6.0 of 10

    FreeScene parses free-form text and image prompts into scene graphs via a VLM-based Graph Designer, then generates 3D indoor layouts with a mixed graph diffusion transformer, reporting improved quality and controllabi...

  8. ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editing

    cs.CV 2025-06 conditional novelty 6.0 of 10

    ReSpace is an autoregressive LLM framework for text-driven 3D indoor scene editing and synthesis, using a structured JSON scene representation and a voxelization-based layout metric.

  9. ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A training-free pipeline that generates editable 3D scenes from text by using a generated 2D image as an intermediary to extract object shapes, appearances, positions, and poses.

  10. Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    Scenethesis integrates LLM planning, vision-guided layout refinement, and SDF-based collision and stability optimization to generate physically plausible interactive 3D scenes from text.

  11. ScanEdit: Hierarchically-Guided Functional 3D Scan Editing

    cs.CV 2025-04 conditional novelty 6.0 of 10

    ScanEdit uses hierarchical scene graphs and LLM-based planning, placement, and optimization to rearrange objects in real-world 3D scans from text instructions.

  12. HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation

    cs.GR 2025-04 conditional novelty 6.0 of 10

    HiScene generates compositional 3D scenes by treating a room as an object under isometric view, then decomposing and regenerating each instance with video-diffusion amodal completion.

  13. LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models

    cs.CV 2024-12 conditional novelty 6.0 of 10

    LayoutVLM couples VLM-generated pose estimates and spatial relations with differentiable optimization to create physically plausible, instruction-aligned 3D layouts.

  14. Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modeling

    cs.CV 2024-11 conditional novelty 6.0 of 10

    Diorama produces a structured, CAD-based 3D scene model from one RGB image using pretrained foundation models and staged layout optimization, with no end-to-end training.

  15. SG-Layout: Structured Scene Graph-Guided Layout Generation with LLMs

    cs.CV 2026-08 conditional novelty 5.0 of 10

    Feeding scene-graph embeddings into a frozen LLM through a two-stage alignment and LoRA pipeline improves layout accuracy in relation-dense scenes, at the cost of small losses on simple two-object layouts.

  16. MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generation

    cs.CV 2025-02 conditional novelty 5.0 of 10

    MMGDreamer generates 3D indoor scenes from a mixed-modality scene graph whose nodes can be text, images, or both, and it predicts missing object relationships for more coherent layouts.

  17. SSEditor: Controllable Mask-to-Scene Generation with Diffusion Model

    cs.CV 2024-11 conditional novelty 5.0 of 10

    SSEditor generates controllable 3D semantic urban scenes from mask conditions using a triplane autoencoder and a mask-conditional diffusion model, avoiding multi-step resampling.

  18. Global Graph-Validated Optimization for VLM-based 3D Indoor Scene Generation

    cs.CV 2026-08 conditional novelty 4.0 of 10

    A graph-verified, evolution-plus-gradient pipeline for text-driven 3D indoor layout generation reports improved GPT-4o-judged semantic and physical quality over four prior methods.

Pith tools