mlsanityData to 14 Oct 2026

Diffusion-Based Attention Warping for Consistent 3D Scene Editing

arXiv 2412.07984 ↗First posted 10 Dec 2024cs.CVcited by 7

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

Abstract (arXiv)

We present a novel method for 3D scene editing using diffusion models, designed to ensure view consistency and realism across perspectives. Our approach leverages attention features extracted from a single reference image to define the intended edits. These features are warped across multiple views by aligning them with scene geometry derived from Gaussian splatting depth estimates. Injecting these warped features into other viewpoints enables coherent propagation of edits, achieving high fidelity and spatial alignment in 3D space. Extensive evaluations demonstrate the effectiveness of our method in generating versatile edits of 3D scenes, significantly advancing the capabilities of scene manipulation compared to the existing methods. Project page: urlhttps://attention-warp.github.io

Key facts. Cited by 7 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 20 of its 70 references that are in the map. First posted on arXiv 10 Dec 2024.

Builds on

20 of 70 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts18 Oct
  2. 2023ED-NeRF: Efficient Text-Guided Editing of 3D Scene with Latent Space NeRF4 Oct
  3. 2023Edit-DiffNeRF: Editing 3D Neural Radiance Fields using 2D Diffusion Model15 Jun
  4. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 16

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2023Segment Anythingcited by 8,234
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  7. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  8. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  9. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  10. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  11. 2023TokenFlow: Consistent Diffusion Features for Consistent Video Editingcited by 442
  12. 2024DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editingcited by 94
4 more
  1. 2022SNeRF: Stylized Neural Implicit Representations for 3D Scenescited by 26
  2. 2022PaletteNeRF: Palette-based Color Editing for NeRFscited by 18
  3. 2023LatentEditor: Text Driven Local Editing of 3D Scenescited by 17
  4. 2023InstructP2P: Learning to Edit 3D Point Clouds with Text Instructionscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
  2. 2026Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editingcited by 4
  3. 2025DisCo3D: Distilling Multi-View Consistency for 3D Scene Editingcited by 3
  4. 2026TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Maskingcited by 2
  5. 2025InstructMix2Mix: Consistent Sparse-View Editing Through Multi-View Model Personalizationcited by 1
  6. 2026GeM-NR: Geometry-Aware Multi-View Editing for Nonrigid Scene Changescited by 0
  7. 2026Stabilizing Camera-Controlled Novel View Synthesis at Inference Timecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Look Before You Edit: Attention-Guided Camera Placement and Multi-View Alignment for 3D Gaussian Splatting Editing
  2. 2024EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting
  3. 2024GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
  4. 2025WAVE: Warp-Based View Guidance for Consistent Novel View Synthesis Using a Single Image
  5. 2024Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-Trained Diffusion Priors
  6. 2024ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing
  7. 2025Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization
  8. 20253D-LATTE: Latent Space 3D Editing from Textual Instructions