PanoDiffusion: 360-degree Panorama Outpainting via Diffusion
On the map: Diffusion models → 3D, point cloud and scene generation
Abstract (arXiv)
Generating complete 360-degree panoramas from narrow field of view images is ongoing research as omnidirectional RGB data is not readily available. Existing GAN-based approaches face some barriers to achieving higher quality output, and have poor generalization performance over different mask types. In this paper, we present our 360-degree indoor RGB-D panorama outpainting model using latent diffusion models (LDM), called PanoDiffusion. We introduce a new bi-modal latent diffusion structure that utilizes both RGB and depth panoramic data during training, which works surprisingly well to outpaint depth-free RGB images during inference. We further propose a novel technique of introducing progressive camera rotations during each diffusion denoising step, which leads to substantial improvement in achieving panorama wraparound consistency. Results show that our PanoDiffusion not only significantly outperforms state-of-the-art methods on RGB-D panorama outpainting by producing diverse well-structured results for different types of masks, but can also synthesize high-quality depth panoramas to provide realistic 3D indoor models.
Key facts. Cited by 51 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 29 of its 44 references that are in the map. First posted on arXiv 6 Jul 2023.
Builds on
29 of 44 references.
Closest ancestors · 2
Same direction, newest first
- 2022SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model9 Dec
- 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Models24 Jan
Other references · 27
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2016Improved Techniques for Training GANscited by 2,970
- 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
- 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 738
- 2018Generative Image Inpainting with Contextual Attentioncited by 580
- 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 434
- 2019Structured3D: A Large Photo-realistic Dataset for Structured 3D Modelingcited by 286
- 2021Generating Images with Sparse Representationscited by 266
- 2022Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpaintingcited by 233
- 2023Inpaint Anything: Segment Anything Meets Image Inpaintingcited by 233
- 2021Large Scale Image Completion via Co-Modulated Generative Adversarial Networkscited by 220
15 more
- 2023MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusioncited by 212
- 2020Non-Local Spatial Propagation Network for Depth Completioncited by 195
- 2019Pluralistic Image Completioncited by 162
- 2017Learning to Predict Indoor Illumination from a Single Imagecited by 161
- 2021High-Fidelity Pluralistic Image Completion with Transformerscited by 134
- 2018Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Networkcited by 110
- 2019Deep Parametric Indoor Lighting Estimationcited by 83
- 2018T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Taskscited by 70
- 2019Neural Illumination: Lighting Prediction for Indoor Environmentscited by 58
- 2020HDR Environment Map Estimation for Real-Time Augmented Realitycited by 47
- 2022Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creationcited by 47
- 2021Bridging Global Context Interactions for High-Fidelity Image Completioncited by 40
- 2022BlobGAN: Spatially Disentangled Scene Representationscited by 35
- 2021BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-aided Adversarial Learningcited by 26
- 2017Joint Layout Estimation and Global Multi-View Registration for Indoor Reconstructioncited by 4
Built on by
Citing papers per year: 2023: 1; 2024: 9; 2025: 24; 2026: 17.
51 papers.
Sort:
By area:
- 2025HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixelscited by 94
- 2024360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Modelcited by 58
- 20244K4DGen: Panoramic 4D Generation at 4K Resolutioncited by 54
- 2024LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generationcited by 53
- 2025CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generationcited by 35
- 2025A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Visioncited by 24
- 20253D Scene Generation: A Surveycited by 24
- 2025DiT360: High-Fidelity Panoramic Image Generation via Hybrid Trainingcited by 24
- 2024PanoFree: Tuning-Free Holistic Multi-view Image Generation with Cross-view Self-Guidancecited by 18
- 2025Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videoscited by 16
- 2025VideoPanda: Video Panoramic Diffusion with Multi-view Attentioncited by 13
- 2025What Makes for Text to 360-degree Panorama Generation with Stable Diffusion?cited by 13
38 more
- 2025DreamCube: 3D Panorama Generation via Multi-plane Synchronizationcited by 12
- 2025Panorama Generation From NFoV Image Done Rightcited by 11
- 2025Omni2: Unifying Omnidirectional Image Generation and Editing in an Omni Modelcited by 9
- 2025Conditional Panoramic Image Generation via Masked Autoregressive Modelingcited by 9
- 2025PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusioncited by 7
- 2026360Anything: Geometry-Free Lifting of Images and Videos to 360degcited by 7
- 2024CamFreeDiff: Camera-free Image to Panorama Generation with Diffusion Modelcited by 5
- 2024OmniDrag: Enabling Motion Control for Omnidirectional Image-to-Video Generationcited by 5
- 2024PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMscited by 4
- 2025OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenescited by 4
- 2025GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstructioncited by 4
- 2026Pantheon360: Taming Digital Twin Generation via 3D-Aware 360deg Video Diffusioncited by 4
- 2026MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffoldcited by 4
- 2025Constructing a 3D Scene from a Single Imagecited by 3
- 2025Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusioncited by 3
- 2025Self-Evolving 3D Scene Generation from a Single Imagecited by 3
- 2026PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesiscited by 3
- 2024PanoDreamer: Optimization-Based Single Image to 360 3D Scene With Diffusioncited by 2
- 2025DreamAnywhere: Object-Centric Panoramic 3D Scene Generationcited by 2
- 2025SE360: Semantic Edit in 360^circ Panoramas via Hierarchical Data Constructioncited by 2
- 2023Increasing diversity of omni-directional images generated from single image using cGAN based on MLPMixercited by 1
- 2025SparsyFed: Sparse Adaptive Federated Trainingcited by 1
- 2026Map2World: Segment Map Conditioned Text to 3D World Generationcited by 1
- 2026CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coveragecited by 1
- 2024FaithFill: Faithful Inpainting for Object Completion Using a Single Reference Imagecited by 0
- 2025Generative Panoramic Image Stitchingcited by 0
- 2025HDR Environment Map Estimation with Latent Diffusion Modelscited by 0
- 2025JoPano: Unified Panorama Generation via Joint Modelingcited by 0
- 2026Gimbal360: Canonicalizing Planar Diffusion for Spherical Panorama Completioncited by 0
- 2026Stepper: Stepwise Immersive Scene Generation with Multiview Panoramascited by 0
- 2026LatentHDR: Decoupling Exposure from Diffusion via Conditional Latent-to-Latent Mapping for Text/Image-to-Panoramic HDRcited by 0
- 2026PanoPlane: Plane-Aware Panoramic Completion for Sparse-View Indoor 3D Gaussian Splattingcited by 0
- 2026SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360^circ Panorama Generationcited by 0
- 2026Unified Panoramic-Gaussian Representation for Monocular 4D Scene Synthesiscited by 0
- 2026Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantificationcited by 0
- 2026Enhancing In-context Panoramic Generation via Geometric-aware Pretrainingcited by 0
- 2026Mover360: Controllable Object Manipulation in 360deg Panoramic Imagescited by 0
- 2026MUGEN: Interactive Panoramic World Exploration via Camera Controlcited by 0
50 most cited of 51 All 51 (JSON)
- 2026DepthTile: Depth-Guided Existing-Image Self-Tiling with Input-Side Tileability Assessment12 Oct 2026
- 2026MUGEN: Interactive Panoramic World Exploration via Camera Control29 Sep 2026
- 2026Mover360: Controllable Object Manipulation in 360deg Panoramic Images24 Aug 2026
- 2026Enhancing In-context Panoramic Generation via Geometric-aware Pretraining9 Jul 2026
- 2026Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification6 Jul 2026
- 2026Unified Panoramic-Gaussian Representation for Monocular 4D Scene Synthesis2 Jul 2026
- 2026MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold11 Jun 2026
- 2026SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360^circ Panorama Generation10 Jun 2026
- 2026Pantheon360: Taming Digital Twin Generation via 3D-Aware 360deg Video Diffusion25 May 2026
- 2026PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesis18 May 2026
- 2026CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage15 May 2026
- 2026PanoPlane: Plane-Aware Panoramic Completion for Sparse-View Indoor 3D Gaussian Splatting13 May 2026
38 more
- 2026LatentHDR: Decoupling Exposure from Diffusion via Conditional Latent-to-Latent Mapping for Text/Image-to-Panoramic HDR11 May 2026
- 2026Map2World: Segment Map Conditioned Text to 3D World Generation1 May 2026
- 2026Stepper: Stepwise Immersive Scene Generation with Multiview Panoramas30 Mar 2026
- 2026Gimbal360: Canonicalizing Planar Diffusion for Spherical Panorama Completion24 Mar 2026
- 2026360Anything: Geometry-Free Lifting of Images and Videos to 360deg22 Jan 2026
- 2025GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction31 Dec 2025
- 2025SE360: Semantic Edit in 360^circ Panoramas via Hierarchical Data Construction23 Dec 2025
- 2025Self-Evolving 3D Scene Generation from a Single Image9 Dec 2025
- 2025JoPano: Unified Panorama Generation via Joint Modeling7 Dec 2025
- 2025OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes30 Oct 2025
- 2025DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training13 Oct 2025
- 2025PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion29 Sep 2025
- 2025Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusion31 Aug 2025
- 2025HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels29 Jul 2025
- 2025HDR Environment Map Estimation with Latent Diffusion Models28 Jul 2025
- 2025Generative Panoramic Image Stitching8 Jul 2025
- 2025DreamAnywhere: Object-Centric Panoramic 3D Scene Generation25 Jun 2025
- 2025DreamCube: 3D Panorama Generation via Multi-plane Synchronization20 Jun 2025
- 2025What Makes for Text to 360-degree Panorama Generation with Stable Diffusion?28 May 2025
- 2025Conditional Panoramic Image Generation via Masked Autoregressive Modeling22 May 2025
- 2025Constructing a 3D Scene from a Single Image21 May 2025
- 20253D Scene Generation: A Survey8 May 2025
- 2025VideoPanda: Video Panoramic Diffusion with Multi-view Attention15 Apr 2025
- 2025Omni2: Unifying Omnidirectional Image Generation and Editing in an Omni Model15 Apr 2025
- 2025Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videos10 Apr 2025
- 2025SparsyFed: Sparse Adaptive Federated Training7 Apr 2025
- 2025Panorama Generation From NFoV Image Done Right24 Mar 2025
- 2025A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision11 Feb 2025
- 2025CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation28 Jan 2025
- 2024OmniDrag: Enabling Motion Control for Omnidirectional Image-to-Video Generation12 Dec 2024
- 2024PanoDreamer: Optimization-Based Single Image to 360 3D Scene With Diffusion6 Dec 2024
- 2024PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMs24 Nov 2024
- 2024LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation23 Aug 2024
- 2024PanoFree: Tuning-Free Holistic Multi-view Image Generation with Cross-view Self-Guidance4 Aug 2024
- 2024CamFreeDiff: Camera-free Image to Panorama Generation with Diffusion Model9 Jul 2024
- 20244K4DGen: Panoramic 4D Generation at 4K Resolution19 Jun 2024
- 2024FaithFill: Faithful Inpainting for Object Completion Using a Single Reference Image12 Jun 2024
- 2024360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model12 Jan 2024
50 newest of 51 All 51 (JSON)
- 2024360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Modelcited by 58
- 2025CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generationcited by 35
- 20253D Scene Generation: A Surveycited by 24
- 2025What Makes for Text to 360-degree Panorama Generation with Stable Diffusion?cited by 13
- 2025PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusioncited by 7
- 2024CamFreeDiff: Camera-free Image to Panorama Generation with Diffusion Modelcited by 5
- 2026Pantheon360: Taming Digital Twin Generation via 3D-Aware 360deg Video Diffusioncited by 4
- 2025Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusioncited by 3
- 2025HDR Environment Map Estimation with Latent Diffusion Modelscited by 0
- 2026Gimbal360: Canonicalizing Planar Diffusion for Spherical Panorama Completioncited by 0
- 2026PanoPlane: Plane-Aware Panoramic Completion for Sparse-View Indoor 3D Gaussian Splattingcited by 0
- 2026Pantheon360: Taming Digital Twin Generation via 3D-Aware 360deg Video Diffusion25 May 2026
- 2026PanoPlane: Plane-Aware Panoramic Completion for Sparse-View Indoor 3D Gaussian Splatting13 May 2026
- 2026Gimbal360: Canonicalizing Planar Diffusion for Spherical Panorama Completion24 Mar 2026
- 2025PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion29 Sep 2025
- 2025Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusion31 Aug 2025
- 2025HDR Environment Map Estimation with Latent Diffusion Models28 Jul 2025
- 2025What Makes for Text to 360-degree Panorama Generation with Stable Diffusion?28 May 2025
- 20253D Scene Generation: A Survey8 May 2025
- 2025CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation28 Jan 2025
- 2024CamFreeDiff: Camera-free Image to Panorama Generation with Diffusion Model9 Jul 2024
- 2024360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model12 Jan 2024
- 2025HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixelscited by 94
- 20244K4DGen: Panoramic 4D Generation at 4K Resolutioncited by 54
- 2024LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generationcited by 53
- 2025A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Visioncited by 24
- 2025DiT360: High-Fidelity Panoramic Image Generation via Hybrid Trainingcited by 24
- 2024PanoFree: Tuning-Free Holistic Multi-view Image Generation with Cross-view Self-Guidancecited by 18
- 2025Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videoscited by 16
- 2025VideoPanda: Video Panoramic Diffusion with Multi-view Attentioncited by 13
- 2025DreamCube: 3D Panorama Generation via Multi-plane Synchronizationcited by 12
- 2025Panorama Generation From NFoV Image Done Rightcited by 11
- 2025Omni2: Unifying Omnidirectional Image Generation and Editing in an Omni Modelcited by 9
- 2025Conditional Panoramic Image Generation via Masked Autoregressive Modelingcited by 9
12 most cited of 37 All 37 (JSON)
- 2026DepthTile: Depth-Guided Existing-Image Self-Tiling with Input-Side Tileability Assessment12 Oct 2026
- 2026MUGEN: Interactive Panoramic World Exploration via Camera Control29 Sep 2026
- 2026Mover360: Controllable Object Manipulation in 360deg Panoramic Images24 Aug 2026
- 2026Enhancing In-context Panoramic Generation via Geometric-aware Pretraining9 Jul 2026
- 2026Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification6 Jul 2026
- 2026Unified Panoramic-Gaussian Representation for Monocular 4D Scene Synthesis2 Jul 2026
- 2026SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360^circ Panorama Generation10 Jun 2026
- 2026CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage15 May 2026
- 2026LatentHDR: Decoupling Exposure from Diffusion via Conditional Latent-to-Latent Mapping for Text/Image-to-Panoramic HDR11 May 2026
- 2026Map2World: Segment Map Conditioned Text to 3D World Generation1 May 2026
- 2026360Anything: Geometry-Free Lifting of Images and Videos to 360deg22 Jan 2026
- 2025GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction31 Dec 2025
12 newest of 37 All 37 (JSON)
Similar, not cited
Close in wording, no citation either way
- 2023360-Degree Panorama Generation from Few Unregistered NFoV Images
- 2023Diffusion360: Seamless 360 Degree Panoramic Image Generation based on Diffusion Models
- 2023Customizing 360-Degree Panoramas through Text-to-Image Diffusion Models
- 2023LDM3D-VR: Latent Diffusion Model for 3D VR
- 2022RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Models
- 2025SphereDiff: Tuning-free 360deg Static and Dynamic Panorama Generation via Spherical Latent Representation
- 2024SpotDiffusion: A Fast Approach For Seamless Panorama Generation Over Time
- 2024StereoDiffusion: Training-Free Stereo Image Generation Using Latent Diffusion Models