mlsanityData to 7 Oct 2026

CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation

arXiv 2501.17162 ↗First posted 28 Jan 2025cs.CV cs.LGcited by 35

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

Abstract (arXiv)

We introduce a novel method for generating 360deg panoramas from text prompts or images. Our approach leverages recent advances in 3D generation by employing multi-view diffusion models to jointly synthesize the six faces of a cubemap. Unlike previous methods that rely on processing equirectangular projections or autoregressive generation, our method treats each face as a standard perspective image, simplifying the generation process and enabling the use of existing multi-view diffusion models. We demonstrate that these models can be adapted to produce high-quality cubemaps without requiring correspondence-aware attention layers. Our model allows for fine-grained text control, generates high resolution panorama images and generalizes well beyond its training set, whilst achieving state-of-the-art results, both qualitatively and quantitatively. Project page: https://cubediff.github.io/

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 38 of its 45 references that are in the map. First posted on arXiv 28 Jan 2025.

Builds on

38 of 45 references.

Closest ancestors · 14

Same direction, newest first

  1. 2024Neural Gaffer: Relighting Any Object via Diffusion11 Jun
  2. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Models16 May
  3. 2024Taming Stable Diffusion for Text to 360deg Panorama Image Generation11 Apr
  4. 2024DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation19 Feb
  5. 2023EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion11 Dec
  6. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation4 Dec
  7. 2023Curved Diffusion: A Generative Model With Optical Geometry Control29 Nov
  8. 2023Diffusion360: Seamless 360 Degree Panoramic Image Generation based on Diffusion Models22 Nov
  9. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  10. 2023PanoDiffusion: 360-degree Panorama Outpainting via Diffusion6 Jul
  11. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation25 May
  12. 2023RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texture18 May
2 more
  1. 2022TetraDiffusion: Tetrahedral Diffusion Models for 3D Shape Generation23 Nov
  2. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 24

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  5. 2022Classifier-Free Diffusion Guidancecited by 5,717
  6. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  7. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  8. 2018Demystifying MMD GANscited by 1,268
  9. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  10. 2019Structured3D: A Large Photo-realistic Dataset for Structured 3D Modelingcited by 285
  11. 2022CLIP-Mesh: Generating textured meshes from text using pretrained image-text modelscited by 281
  12. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 211
12 more
  1. 2023MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusioncited by 210
  2. 2017Learning to Predict Indoor Illumination from a Single Imagecited by 160
  3. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 134
  4. 2023ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Modelscited by 127
  5. 2023DiffCollage: Parallel Generation of Large Content with Diffusion Modelscited by 100
  6. 2022Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creationcited by 47
  7. 2020HDR Environment Map Estimation for Real-Time Augmented Realitycited by 46
  8. 2023360-Degree Panorama Generation from Few Unregistered NFoV Imagescited by 42
  9. 2023Autoregressive Omni-Aware Outpainting for Open-Vocabulary 360-Degree Image Generationcited by 33
  10. 2024IllumiNeRF: 3D Relighting Without Inverse Renderingcited by 29
  11. 2023DreamSpace: Dreaming Your Room Space with Text-Driven Panoramic Texture Propagationcited by 25
  12. 2024OPa-Ma: Text Guided Mamba for 360-degree Image Out-paintingcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 20; 2026: 15.

35 papers.

Sort:

By area:

  1. 2025HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixelscited by 91
  2. 2026HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worldscited by 34
  3. 20253D Scene Generation: A Surveycited by 24
  4. 2025DiT360: High-Fidelity Panoramic Image Generation via Hybrid Trainingcited by 24
  5. 2025DA2: Depth Anything in Any Directioncited by 22
  6. 2025Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videoscited by 14
  7. 2025A Recipe for Generating 3D Worlds From a Single Imagecited by 13
  8. 2025What Makes for Text to 360-degree Panorama Generation with Stable Diffusion?cited by 13
  9. 2025DreamCube: 3D Panorama Generation via Multi-plane Synchronizationcited by 12
  10. 2025DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformercited by 10
  11. 2025M2SVid: End-to-End Inpainting and Refinement for Monocular-to-Stereo Video Conversioncited by 10
  12. 2025Conditional Panoramic Image Generation via Masked Autoregressive Modelingcited by 9
23 more
  1. 2026CubeComposer: Spatio-Temporal Autoregressive 4K 360deg Video Generation from Perspective Videocited by 8
  2. 2026360Anything: Geometry-Free Lifting of Images and Videos to 360degcited by 7
  3. 2025OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenescited by 4
  4. 2025GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstructioncited by 4
  5. 2026Pantheon360: Taming Digital Twin Generation via 3D-Aware 360deg Video Diffusioncited by 4
  6. 2025TanDiT: Tangent-Plane Diffusion Transformer for High-Quality 360deg Panorama Generationcited by 3
  7. 2025DreamAnywhere: Object-Centric Panoramic 3D Scene Generationcited by 2
  8. 2025Generative Blocks World: Moving Things Around in Picturescited by 2
  9. 2025SE360: Semantic Edit in 360^circ Panoramas via Hierarchical Data Constructioncited by 2
  10. 2026SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPEcited by 2
  11. 2026Pano2World: End-to-End 3D Generation via Unified Multi-View Sequencescited by 2
  12. 2026Unified Panoramic Geometry Estimation via Multi-View Foundation Modelscited by 1
  13. 2025A Survey on Text-Driven 360-Degree Panorama Generationcited by 0
  14. 2025Top2Pano: Learning to Generate Indoor Panoramas from Top-Down Viewcited by 0
  15. 2025JoPano: Unified Panorama Generation via Joint Modelingcited by 0
  16. 2026Scene Generation at Absolute Scale: Utilizing Semantic and Geometric Guidance From Text for Accurate and Interpretable 3D Indoor Scene Generationcited by 0
  17. 2026Gimbal360: Canonicalizing Planar Diffusion for Spherical Panorama Completioncited by 0
  18. 2026Stepper: Stepwise Immersive Scene Generation with Multiview Panoramascited by 0
  19. 2026Probing CLIP's Comprehension of 360-Degree Textual and Visual Semanticscited by 0
  20. 2026SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360^circ Panorama Generationcited by 0
  21. 2026Enhancing In-context Panoramic Generation via Geometric-aware Pretrainingcited by 0
  22. 2026Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generationcited by 0
  23. 2026World Observer: Joint Actor-Observer Generation for Persistent World Modelingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Customizing 360-Degree Panoramas through Text-to-Image Diffusion Models
  2. 2024Merging and Splitting Diffusion Paths for Semantically Coherent Panoramas
  3. 2024DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion
  4. 2024Multi-Scale Diffusion: Enhancing Spatial Layout in High-Resolution Panoramic Image Generation
  5. 2022HORIZON: High-Resolution Semantically Controlled Panorama Synthesis
  6. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation
  7. 2024SpotDiffusion: A Fast Approach For Seamless Panorama Generation Over Time
  8. 2025ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models