mlsanityData to 7 Oct 2026

Tree-D Fusion: Simulation-Ready Tree Dataset from Single Images with Diffusion Priors

arXiv 2407.10330 ↗First posted 14 Jul 2024cs.CVcited by 13

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

Abstract (arXiv)

We introduce Tree D-fusion, featuring the first collection of 600,000 environmentally aware, 3D simulation-ready tree models generated through Diffusion priors. Each reconstructed 3D tree model corresponds to an image from Google's Auto Arborist Dataset, comprising street view images and associated genus labels of trees across North America. Our method distills the scores of two tree-adapted diffusion models by utilizing text prompts to specify a tree genus, thus facilitating shape reconstruction. This process involves reconstructing a 3D tree envelope filled with point markers, which are subsequently utilized to estimate the tree's branching structure using the space colonization algorithm conditioned on a specified genus.

Key facts. Cited by 13 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 46 of its 135 references that are in the map. First posted on arXiv 14 Jul 2024.

Builds on

46 of 135 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors30 Jun
  2. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation25 May
  3. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  4. 2022NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors6 Dec
  5. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation1 Dec
  6. 2022NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg Views29 Nov
  7. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  7. 2023Segment Anythingcited by 8,158
  8. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  9. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  10. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  11. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  12. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
27 more
  1. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  2. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  3. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  4. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  5. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 837
  6. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  7. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  8. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  9. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  10. 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
  11. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  12. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  13. 2022A high-resolution canopy height model of the Earthcited by 91
  14. 2020Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Imagescited by 79
  15. 2021Multi-view 3D Reconstruction with Transformercited by 52
  16. 2018Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstructioncited by 44
  17. 2022Multi-View Mesh Reconstruction with Neural Deferred Shadingcited by 44
  18. 2022Topologically-Aware Deformation Fields for Single-View 3D Reconstructioncited by 29
  19. 2023FOR-instance: a UAV laser scanning benchmark dataset for semantic and instance segmentation of individual treescited by 21
  20. 2017Fine-Grained Object Recognition and Zero-Shot Learning in Remote Sensing Imagerycited by 17
  21. 2019From Google Maps to a Fine-Grained Catalog of Street treescited by 15
  22. 2022Individual Tree Detection in Large-Scale Urban Environments using High-Resolution Multispectral Imagerycited by 11
  23. 2023DeepTree: Modeling Trees with Situated Latentscited by 9
  24. 2020Procedural Urban Forestrycited by 4
  25. 2018Probabilistic Plant Modeling via Multi-View Image-to-Image Translationcited by 3
  26. 2021Weakly Supervised Instance Attention for Multisource Fine-Grained Object Recognition with an Application to Tree Species Classificationcited by 2
  27. 2021RandCrowns: A Quantitative Metric for Imprecisely Labeled Tree Crown Delineationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 8; 2026: 3.

13 papers.

Sort:

By area:

  1. 2024RGB2Point: 3D Point Cloud Generation from Single RGB Imagescited by 7
  2. 2024DivShift: Exploring Domain-Specific Distribution Shifts in Large-Scale, Volunteer-Collected Biodiversity Datasetscited by 4
  3. 2025Autoregressive Generation of Static and Growing Treescited by 3
  4. 2025PlantDreamer: Achieving Realistic 3D Plant Models with Diffusion-Guided Gaussian Splattingcited by 3
  5. 2025X-GAN: A Generative AI-Powered Unsupervised Model for Main Vessel Segmentation of Glaucoma Screeningcited by 2
  6. 2026TreeSRNF: Square-Root Normal Fields for Generative Modelling of the Geometric and Structural Variability in Tree-like 3D Objectscited by 1
  7. 2025DATR: Diffusion-based 3D Apple Tree Reconstruction Framework with Sparse-Viewcited by 0
  8. 2025ProcGen3D: Learning Neural Procedural Graph Representations for Image-to-3D Reconstructioncited by 0
  9. 2025Top2Ground: A Height-Aware Dual Conditioning Diffusion Model for Robust Aerial-to-Ground View Generationcited by 0
  10. 2025Learning to Predict Aboveground Biomass from RGB Images with 3D Synthetic Scenescited by 0
  11. 2025FloraForge: LLM-Assisted Procedural Generation of Editable and Analysis-Ready 3D Plant Geometric Models For Agricultural Applicationscited by 0
  12. 2026NEST3D: A High-Resolution Multimodal Dataset of Sociable Weaver Tree Nestscited by 0
1 more
  1. 2026Growing a Stand, Not a Tree: Joint Canopy Generation Reproduces Crown Shynesscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025From Canopy to Ground via ForestGen3D: Learning Cross-Domain Generation of 3D Forest Structure from Aerial-to-Terrestrial LiDAR
  2. 2026Autoregressive Frontier Expansion: Growing Trees with Graph Machine Learning
  3. 2025Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models
  4. 2025Data Augmentation and Resolution Enhancement using GANs and Diffusion Models for Tree Segmentation
  5. 20253D Reconstruction and Information Fusion between Dormant and Canopy Seasons in Commercial Orchards Using Deep Learning and Fast GICP
  6. 2026Diffusion Transformers for Roof Graph Synthesis and Reconstruction
  7. 2025WHU-STree: A Multi-modal Benchmark Dataset for Street Tree Inventory
  8. 2024LT3SD: Latent Trees for 3D Scene Diffusion