mlsanityData to 14 Oct 2026

EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting

arXiv 2412.11520 ↗First posted 16 Dec 2024cs.CV cs.AIcited by 41

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

Recent advancements in 3D editing have highlighted the potential of text-driven methods in real-time, user-friendly AR/VR applications. However, current methods rely on 2D diffusion models without adequately considering multi-view information, resulting in multi-view inconsistency. While 3D Gaussian Splatting (3DGS) significantly improves rendering quality and speed, its 3D editing process encounters difficulties with inefficient optimization, as pre-trained Gaussians retain excessive source information, hindering optimization. To address these limitations, we propose EditSplat, a novel text-driven 3D scene editing framework that integrates Multi-view Fusion Guidance (MFG) and Attention-Guided Trimming (AGT). Our MFG ensures multi-view consistency by incorporating essential multi-view information into the diffusion process, leveraging classifier-free guidance from the text-to-image diffusion model and the geometric structure inherent to 3DGS. Additionally, our AGT utilizes the explicit representation of 3DGS to selectively prune and optimize 3D Gaussians, enhancing optimization efficiency and enabling precise, semantically rich local editing. Through extensive qualitative and quantitative evaluations, EditSplat achieves state-of-the-art performance, establishing a new benchmark for text-driven 3D scene editing.

Key facts. Cited by 41 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 53 of its 59 references that are in the map. First posted on arXiv 16 Dec 2024.

Builds on

53 of 59 references.

Closest ancestors · 10

Same direction, newest first

  1. 20243DEgo: 3D Editing on the Go!14 Jul
  2. 2024ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing13 Jun
  3. 2024DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data6 Jun
  4. 2023Free-Editor: Zero-shot Text-driven 3D Scene Editing21 Dec
  5. 2023ED-NeRF: Efficient Text-Guided Editing of 3D Scene with Latent Space NeRF4 Oct
  6. 2023HoloDiffusion: Training a 3D Diffusion Model using 2D Images29 Mar
  7. 20223D Neural Field Generation using Triplane Diffusion30 Nov
  8. 2022Magic3D: High-Resolution Text-to-3D Content Creation18 Nov
  9. 2022RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation17 Nov
  10. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 43

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  7. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  8. 2020Denoising Diffusion Implicit Modelscited by 9,781
  9. 2023Segment Anythingcited by 8,234
  10. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  11. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  12. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
31 more
  1. 2022Scalable Diffusion Models with Transformerscited by 6,054
  2. 2022Classifier-Free Diffusion Guidancecited by 5,847
  3. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  4. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  5. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  6. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  8. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  9. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  10. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  11. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  12. 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
  13. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,163
  14. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 624
  15. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  16. 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 484
  17. 2023GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splattingcited by 335
  18. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 214
  19. 2023FreeU: Free Lunch in Diffusion U-Netcited by 196
  20. 2023DreamEditor: Text-Driven 3D Scene Editing with Neural Fieldscited by 155
  21. 2024Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editingcited by 135
  22. 2024GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editingcited by 115
  23. 2023Inversion-Free Image Editing with Natural Languagecited by 106
  24. 2024DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editingcited by 94
  25. 2023FocalDreamer: Text-driven 3D Editing via Focal-fusion Assemblycited by 76
  26. 2024ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fieldscited by 68
  27. 2024View-Consistent 3D Editing with Gaussian Splattingcited by 67
  28. 2023Watch Your Steps: Local Image and Scene Editing by Text Instructionscited by 50
  29. 2023Posterior Distillation Samplingcited by 46
  30. 2023Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Trainingcited by 21
  31. 2024TrAME: Trajectory-Anchored Multi-View Editing for Text-Guided 3D Gaussian Splatting Manipulationcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 19; 2026: 22.

41 papers.

Sort:

By area:

  1. 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
  2. 20253D-LATTE: Latent Space 3D Editing from Textual Instructionscited by 11
  3. 2025AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editingcited by 10
  4. 2025Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimizationcited by 9
  5. 2025CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splattingcited by 8
  6. 2025CoreEditor: Correspondence-constrained Diffusion for Consistent 3D Editingcited by 5
  7. 2025Optimized Minimal 4D Gaussian Splattingcited by 5
  8. 2025Attention in Diffusion Model: A Surveycited by 4
  9. 2026Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editingcited by 4
  10. 2025DisCo3D: Distilling Multi-View Consistency for 3D Scene Editingcited by 3
  11. 2025Personalize Your Gaussian: Consistent 3D Scene Personalization from a Single Imagecited by 2
  12. 2025Learning Unified Representation of 3D Gaussian Splattingcited by 2
29 more
  1. 20253D-Consistent Multi-View Editing by Correspondence Guidancecited by 2
  2. 2025Dynamic-eDiTor: Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformercited by 2
  3. 2025Edit3r: Instant 3D Scene Editing from Sparse Unposed Imagescited by 2
  4. 2026Intellectual Property Protection for 3D Gaussian Splatting Assets: A Surveycited by 2
  5. 2026TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Maskingcited by 2
  6. 2026Neural Gabor Splatting: Enhanced Gaussian Splatting with Neural Gabor for High-frequency Surface Reconstructioncited by 2
  7. 2026Physics-Aware 3D Gaussian Editing for Driving Scene Generationcited by 2
  8. 2025Gen-LangSplat: Generalized Language Gaussian Splatting with Pre-Trained Feature Compressioncited by 1
  9. 2025Error-Driven Scene Editing for 3D Grounding in Large Language Modelscited by 1
  10. 2025ReCoGS: Real-time ReColoring for Gaussian Splatting scenescited by 1
  11. 2026TransSplat: Unbalanced Semantic Transport for Language-Driven 3DGS Editingcited by 1
  12. 2026JointEdit3D: Feed-Forward 3D Scene Editing in a Unified Latent Spacecited by 1
  13. 2026Chat-Edit-3D++: Interactive 3D and 4D Scene Editing via Large Language Modelscited by 1
  14. 2025Mastering Regional 3DGS: Locating, Initializing, and Editing with Diverse 2D Priorscited by 0
  15. 2025InStyle: Instant Appearance Stylization of 3D Shapescited by 0
  16. 2026ATATA: One Algorithm to Align Them Allcited by 0
  17. 2026LightHarmony3D: Harmonizing Illumination and Shadows for Object Insertion in 3D Gaussian Splattingcited by 0
  18. 2026Information-Regularized Constrained Inversion for Stable Avatar Editing from Sparse Supervisioncited by 0
  19. 2026View-Consistent 3D Scene Editing via Dual-Path Structural Correspondense and Semantic Continuitycited by 0
  20. 2026FluSplat: Sparse-View 3D Editing without Test-Time Optimizationcited by 0
  21. 2026GuardMarkGS: Unified Ownership Tracing and Edit Deterrence for 3D Gaussian Splattingcited by 0
  22. 2026VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Predictioncited by 0
  23. 20263DEditSafe: Defending 3D Editing Pipelines from Unsafe Generationcited by 0
  24. 2026Splatshot: 3D Face Avatar Generation from a Single Unconstrained Photocited by 0
  25. 2026TASE: Truncation-Aware Semantic Embeddings for 3D Scene Understanding and Editingcited by 0
  26. 2026GeM-NR: Geometry-Aware Multi-View Editing for Nonrigid Scene Changescited by 0
  27. 2026ReAge3D: Re-Aging 3D Faces with View Consistencycited by 0
  28. 2026From Sparse and Imperfect 2D Anchors to Consistent 3D Gaussian Street Scenes: Support-Aware Appearancecited by 0
  29. 2026UMAS3D: Unified Mask-Free 3D Editing with Region-Adaptive Source Preservationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026SVGS: Single-View to 3D Object Editing via Gaussian Splatting
  2. 2026Look Before You Edit: Attention-Guided Camera Placement and Multi-View Alignment for 3D Gaussian Splatting Editing
  3. 2024SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis
  4. 2024Diffusion-Based Attention Warping for Consistent 3D Scene Editing
  5. 2025ProSplat: Improved Feed-Forward 3D Gaussian Splatting for Wide-Baseline Sparse Views
  6. 2024Localized Gaussian Splatting Editing with Contextual Awareness
  7. 2024ProEdit: Simple Progression is All You Need for High-Quality 3D Scene Editing
  8. 2024GSEdit: Efficient Text-Guided Editing of 3D Objects via Gaussian Splatting