mlsanityData to 7 Oct 2026

ScanEdit: Hierarchically-Guided Functional 3D Scan Editing

arXiv 2504.15049 ↗First posted 21 Apr 2025cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

With the fast pace of 3D capture technology and resulting abundance of 3D data, effective 3D scene editing becomes essential for a variety of graphics applications. In this work we present ScanEdit, an instruction-driven method for functional editing of complex, real-world 3D scans. To model large and interdependent sets of ob- jectswe propose a hierarchically-guided approach. Given a 3D scan decomposed into its object instances, we first construct a hierarchical scene graph representation to enable effective, tractable editing. We then leverage reason- ing capabilities of Large Language Models (LLMs) and translate high-level language instructions into actionable commands applied hierarchically to the scene graph. Fi- nally, ScanEdit integrates LLM-based guidance with ex- plicit physical constraints and generates realistic scenes where object arrangements obey both physics and common sense. In our extensive experimental evaluation ScanEdit outperforms state of the art and demonstrates excellent re- sults for a variety of real-world scenes and input instruc- tions.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 42 of its 94 references that are in the map. First posted on arXiv 21 Apr 2025.

Builds on

42 of 94 references.

References · 42

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Denoising Diffusion Implicit Modelscited by 9,655
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  5. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  6. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 885
  7. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
  8. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
  9. 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 482
  10. 2023LayoutGPT: Compositional Visual Planning and Generation with Large Language Modelscited by 337
  11. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 299
  12. 2023Holodeck: Language Guided Generation of 3D Embodied AI Environmentscited by 257
30 more
  1. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  2. 2021ATISS: Autoregressive Transformers for Indoor Scene Synthesiscited by 195
  3. 2023GaussianEditor: Editing 3D Gaussians Delicately with Text Instructionscited by 166
  4. 2023DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesiscited by 159
  5. 2020SceneFormer: Indoor Scene Generation with Transformerscited by 154
  6. 2024SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Codecited by 125
  7. 2023Vox-E: Text-guided Voxel Editing of 3D Objectscited by 114
  8. 2024InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Priorcited by 110
  9. 2018Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Modelscited by 105
  10. 2024GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splattingcited by 104
  11. 2024LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Modelscited by 94
  12. 2024I-Design: Personalized LLM Interior Designercited by 87
  13. 2023AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homescited by 81
  14. 2023LEGO-Net: Learning Regular Rearrangements of Objects in Roomscited by 75
  15. 2018Human-centric Indoor Scene Synthesis Using Stochastic Grammarcited by 73
  16. 2018Deep Generative Modeling for Scene Synthesis via Hybrid Representationscited by 63
  17. 2024InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Priorcited by 55
  18. 2023RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texturecited by 53
  19. 2024Generic 3D Diffusion Adapter Using Controlled Multi-View Editingcited by 46
  20. 2024Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databasescited by 43
  21. 2024SceneTeller: Language-to-3D Scene Generationcited by 43
  22. 20233D Paintbrush: Local Stylization of 3D Shapes with Cascaded Score Distillationcited by 34
  23. 2024Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Imagescited by 34
  24. 2021Scene Synthesis via Uncertainty-Driven Attribute Synchronizationcited by 29
  25. 2021Indoor Scene Generation from a Collection of Semantic-Segmented Depth Imagescited by 27
  26. 2024PrEditor3D: Fast and Precise 3D Shape Editingcited by 27
  27. 2024SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generationcited by 24
  28. 2025FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placementcited by 24
  29. 2024Interactive3D: Create What You Want by Interactive 3D Generationcited by 21
  30. 2024Lay-A-Scene: Personalized 3D Object Arrangement Using Text-to-Image Priorscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026HDSL: A Hierarchical Domain-Specific Language for Structured 3D Indoor Scene Generation and Localized Editing with LLM Agentscited by 2
  2. 2026Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrievalcited by 1
  3. 2026SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenescited by 1
  4. 2026PhyScene3D: Physically Consistent Interactive 3D Tabletop Scene Generationcited by 1