# Geometry-Aware Diffusion Models for Multiview Scene Inpainting

arXiv: https://arxiv.org/abs/2502.13335 · HTML: https://mlsanity.com/paper/2502.13335/

## Key facts

- Cited by 6 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 77 of its 93 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## 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, 30 of 77)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items](https://mlsanity.com/paper/2204.11918/) (2022)
- [Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation](https://mlsanity.com/paper/2212.00774/) (2022)
- [Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model](https://mlsanity.com/paper/2310.15110/) (2023)
- [Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions](https://mlsanity.com/paper/2303.12789/) (2023)
- [CAT3D: Create Anything in 3D with Multi-View Diffusion Models](https://mlsanity.com/paper/2405.10314/) (2024)
- [ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis](https://mlsanity.com/paper/2409.02048/) (2024)
- [Gaussian Grouping: Segment and Edit Anything in 3D Scenes](https://mlsanity.com/paper/2312.00732/) (2023)
- [GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting](https://mlsanity.com/paper/2311.14521/) (2023)
- [Generative Novel View Synthesis with 3D-Aware Diffusion Models](https://mlsanity.com/paper/2304.02602/) (2023)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models](https://mlsanity.com/paper/2303.11989/) (2023)

## Built on by (most cited first, 6 of 6)

- [GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence](https://mlsanity.com/paper/2511.21945/) (2025)
- [Omni-3DEdit: Generalized Versatile 3D Editing in One-Pass](https://mlsanity.com/paper/2603.17841/) (2026)
- [GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image Completion](https://mlsanity.com/paper/2510.03110/) (2025)
- [SplatFill: 3D Scene Inpainting via Depth-Guided Gaussian Splatting](https://mlsanity.com/paper/2509.07809/) (2025)
- [DeclutterNeRF: Generative-Free 3D Scene Recovery for Occlusion Removal](https://mlsanity.com/paper/2504.04679/) (2025)
- [VEIGAR: View-consistent Explicit Inpainting and Geometry Alignment for 3D object Removal](https://mlsanity.com/paper/2506.15821/) (2025)

## Abstract (arXiv)

In this paper, we focus on 3D scene inpainting, where parts of an input image set, captured from different viewpoints, are masked out. The main challenge lies in generating plausible image completions that are geometrically consistent across views. Most recent work addresses this challenge by combining generative models with a 3D radiance field to fuse information across a relatively dense set of viewpoints. However, a major drawback of these methods is that they often produce blurry images due to the fusion of inconsistent cross-view images. To avoid blurry inpaintings, we eschew the use of an explicit or implicit radiance field altogether and instead fuse cross-view information in a learned space. In particular, we introduce a geometry-aware conditional generative model, capable of multi-view consistent inpainting using reference-based geometric and appearance cues. A key advantage of our approach over existing methods is its unique ability to inpaint masked scenes with a limited number of views (i.e., few-view inpainting), whereas previous methods require relatively large image sets for their 3D model fitting step. Empirically, we evaluate and compare our scene-centric inpainting method on two datasets, SPIn-NeRF and NeRFiller, which contain images captured at narrow and wide baselines, respectively, and achieve state-of-the-art 3D inpainting performance on both. Additionally, we demonstrate the efficacy of our approach in the few-view setting compared to prior methods.