mlsanityData to 14 Oct 2026

Top2Ground: A Height-Aware Dual Conditioning Diffusion Model for Robust Aerial-to-Ground View Generation

arXiv 2511.08258 ↗First posted 11 Nov 2025cs.CVcited by 0

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

Abstract (arXiv)

Generating ground-level images from aerial views is a challenging task due to extreme viewpoint disparity, occlusions, and a limited field of view. We introduce Top2Ground, a novel diffusion-based method that directly generates photorealistic ground-view images from aerial input images without relying on intermediate representations such as depth maps or 3D voxels. Specifically, we condition the denoising process on a joint representation of VAE-encoded spatial features (derived from aerial RGB images and an estimated height map) and CLIP-based semantic embeddings. This design ensures the generation is both geometrically constrained by the scene's 3D structure and semantically consistent with its content. We evaluate Top2Ground on three diverse datasets: CVUSA, CVACT, and the Auto Arborist. Our approach shows 7.3% average improvement in SSIM across three benchmark datasets, showing Top2Ground can robustly handle both wide and narrow fields of view, highlighting its strong generalization capabilities.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 30 of its 36 references that are in the map. First posted on arXiv 11 Nov 2025.

Builds on

30 of 36 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Tree-D Fusion: Simulation-Ready Tree Dataset from Single Images with Diffusion Priors14 Jul
  2. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  3. 2022Novel View Synthesis with Diffusion Models6 Oct
  4. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 26

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  7. 2022Classifier-Free Diffusion Guidancecited by 5,847
  8. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  9. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  10. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  11. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  12. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 642
14 more
  1. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 503
  2. 2022BBDM: Image-to-image Translation with Brownian Bridge Diffusion Modelscited by 225
  3. 2020VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrievalcited by 189
  4. 2015Wide-Area Image Geolocalization with Aerial Reference Imagerycited by 186
  5. 2019Lending Orientation to Neural Networks for Cross-view Geo-localizationcited by 180
  6. 2019Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translationcited by 97
  7. 2019Optimal Feature Transport for Cross-View Image Geo-Localizationcited by 91
  8. 2016Predicting Ground-Level Scene Layout from Aerial Imagerycited by 90
  9. 2018Cross-View Image Synthesis using Conditional GANscited by 69
  10. 2021Geometry-Guided Street-View Panorama Synthesis from Satellite Imagerycited by 41
  11. 2023Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairscited by 29
  12. 2020Sat2Vid: Street-view Panoramic Video Synthesis from a Single Satellite Imagecited by 25
  13. 2024Depth Any Canopy: Leveraging Depth Foundation Models for Canopy Height Estimationcited by 12
  14. 2025EarthView: A Large Scale Remote Sensing Dataset for Self-Supervisioncited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Aerial Diffusion: Text Guided Ground-to-Aerial View Translation from a Single Image using Diffusion Models
  2. 2025Satellite to GroundScape -- Large-scale Consistent Ground View Generation from Satellite Views
  3. 2024Leveraging BEV Paradigm for Ground-to-Aerial Image Synthesis
  4. 2025EarthCrafter: Scalable 3D Earth Generation via Dual-Sparse Latent Diffusion
  5. 2026Landscape-Awareness for Geometric View Diffusion Model
  6. 2022Multi-Class Segmentation from Aerial Views using Recursive Noise Diffusion
  7. 2026SparseGF: A Height-Aware Sparse Segmentation Framework with Context Compression for Robust Ground Filtering Across Urban to Natural Scenes
  8. 2024Geometry-guided Cross-view Diffusion for One-to-many Cross-view Image Synthesis