mlsanityData to 14 Oct 2026

3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting

arXiv 2405.18424 ↗First posted 28 May 2024cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

Scene image editing is crucial for entertainment, photography, and advertising design. Existing methods solely focus on either 2D individual object or 3D global scene editing. This results in a lack of a unified approach to effectively control and manipulate scenes at the 3D level with different levels of granularity. In this work, we propose 3DitScene, a novel and unified scene editing framework leveraging language-guided disentangled Gaussian Splatting that enables seamless editing from 2D to 3D, allowing precise control over scene composition and individual objects. We first incorporate 3D Gaussians that are refined through generative priors and optimization techniques. Language features from CLIP then introduce semantics into 3D geometry for object disentanglement. With the disentangled Gaussians, 3DitScene allows for manipulation at both the global and individual levels, revolutionizing creative expression and empowering control over scenes and objects. Experimental results demonstrate the effectiveness and versatility of 3DitScene in scene image editing. Code and online demo can be found at our project homepage: https://zqh0253.github.io/3DitScene/.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 44 of its 55 references that are in the map. First posted on arXiv 28 May 2024.

Builds on

44 of 55 references.

References · 44

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2023Segment Anythingcited by 8,234
  5. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  6. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  7. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  8. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  9. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  10. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  11. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  12. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
32 more
  1. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  2. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  3. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  4. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
  5. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 737
  6. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 642
  7. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  8. 2023AnyDoor: Zero-shot Object-level Image Customizationcited by 412
  9. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 397
  10. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 394
  11. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  12. 2023Faster Segment Anything: Towards Lightweight SAM for Mobile Applicationscited by 352
  13. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 286
  14. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 274
  15. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  16. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 258
  17. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  18. 2019On the "steerability" of generative adversarial networkscited by 248
  19. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  20. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 231
  21. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 214
  22. 2024GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generationcited by 153
  23. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  24. 2019Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesiscited by 106
  25. 2020Generative Hierarchical Features from Synthesizing Imagescited by 83
  26. 2020Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis from a Single Imagecited by 77
  27. 2023SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collectionscited by 72
  28. 2023OBJECT 3DIT: Language-guided 3D-aware Image Editingcited by 63
  29. 2022Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Imagescited by 59
  30. 2023SceneWiz3D: Towards Text-guided 3D Scene Compositioncited by 54
  31. 2024Disentangled 3D Scene Generation with Layout Learningcited by 33
  32. 2023ShowRoom3D: Text to High-Quality 3D Room Generation Using 3D Priorscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 13; 2026: 10.

25 papers.

Sort:

By area:

  1. 2024Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generationcited by 34
  2. 20243DSceneEditor: Controllable 3D Scene Editing with Gaussian Splattingcited by 22
  3. 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
  4. 2025VideoHandles: Editing 3D Object Compositions in Videos Using Video Generative Priorscited by 14
  5. 2025I2V3D: Controllable image-to-video generation with 3D guidancecited by 9
  6. 2025Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimizationcited by 9
  7. 2025SceneDesigner: Controllable Multi-Object Image Generation with 9-DoF Pose Manipulationcited by 9
  8. 2026SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image Generationcited by 4
  9. 2026Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editingcited by 4
  10. 2025High-fidelity 3D Gaussian Inpainting: preserving multi-view consistency and photorealistic detailscited by 3
  11. 2025AnimateScene: Camera-controllable Animation in Any Scenecited by 3
  12. 2025Free-Form Scene Editor: Enabling Multi-Round Object Manipulation like in a 3D Enginecited by 3
13 more
  1. 2026SonoWorld: From One Image to a 3D Audio-Visual Scenecited by 3
  2. 2025Personalize Your Gaussian: Consistent 3D Scene Personalization from a Single Imagecited by 2
  3. 2026Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenescited by 2
  4. 2026TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Maskingcited by 2
  5. 2025Object-X: Learning to Reconstruct Multi-Modal 3D Object Representationscited by 1
  6. 2025CoRe-GS: Coarse-to-Refined Gaussian Splatting with Semantic Object Focuscited by 1
  7. 2025Mono4DEditor: Text-Driven 4D Scene Editing from Monocular Video via Point-Level Localization of Language-Embedded Gaussianscited by 1
  8. 2026PhyEdit: Towards Real-World Object Manipulation via Physically-Grounded Image Editingcited by 1
  9. 2026JointEdit3D: Feed-Forward 3D Scene Editing in a Unified Latent Spacecited by 1
  10. 2026GeoEdit: Geometry-Aware Object Editing via Dual-Branch Denoisingcited by 1
  11. 2025Drag4D: Align Your Motion with Text-Driven 3D Scene Generationcited by 0
  12. 2026BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extractioncited by 0
  13. 20263DEditSafe: Defending 3D Editing Pipelines from Unsafe Generationcited by 0