# Diffusion-Based Attention Warping for Consistent 3D Scene Editing

arXiv: https://arxiv.org/abs/2412.07984 · HTML: https://mlsanity.com/paper/2412.07984/

## 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.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 20 of 20)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [TokenFlow: Consistent Diffusion Features for Consistent Video Editing](https://mlsanity.com/paper/2307.10373/) (2023)
- [DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing](https://mlsanity.com/paper/2404.18929/) (2024)
- [Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts](https://mlsanity.com/paper/2310.11784/) (2023)
- [SNeRF: Stylized Neural Implicit Representations for 3D Scenes](https://mlsanity.com/paper/2207.02363/) (2022)
- [Edit-DiffNeRF: Editing 3D Neural Radiance Fields using 2D Diffusion Model](https://mlsanity.com/paper/2306.09551/) (2023)
- [ED-NeRF: Efficient Text-Guided Editing of 3D Scene with Latent Space NeRF](https://mlsanity.com/paper/2310.02712/) (2023)
- [PaletteNeRF: Palette-based Color Editing for NeRFs](https://mlsanity.com/paper/2212.12871/) (2022)
- [LatentEditor: Text Driven Local Editing of 3D Scenes](https://mlsanity.com/paper/2312.09313/) (2023)
- [InstructP2P: Learning to Edit 3D Point Clouds with Text Instructions](https://mlsanity.com/paper/2306.07154/) (2023)

## Built on by (most cited first, 7 of 7)

- [A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation](https://mlsanity.com/paper/2508.09977/) (2025)
- [Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editing](https://mlsanity.com/paper/2603.03143/) (2026)
- [DisCo3D: Distilling Multi-View Consistency for 3D Scene Editing](https://mlsanity.com/paper/2508.01684/) (2025)
- [TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking](https://mlsanity.com/paper/2604.01207/) (2026)
- [InstructMix2Mix: Consistent Sparse-View Editing Through Multi-View Model Personalization](https://mlsanity.com/paper/2511.14899/) (2025)
- [GeM-NR: Geometry-Aware Multi-View Editing for Nonrigid Scene Changes](https://mlsanity.com/paper/2606.05142/) (2026)
- [Stabilizing Camera-Controlled Novel View Synthesis at Inference Time](https://mlsanity.com/paper/2609.03639/) (2026)

## 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