mlsanityData to 7 Oct 2026

Autoregressive Generation of Static and Growing Trees

arXiv 2502.04762 ↗First posted 7 Feb 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

We propose a transformer architecture and training strategy for tree generation. The architecture processes data at multiple resolutions and has an hourglass shape, with middle layers processing fewer tokens than outer layers. Similar to convolutional networks, we introduce longer range skip connections to completent this multi-resolution approach. The key advantage of this architecture is the faster processing speed and lower memory consumption. We are therefore able to process more complex trees than would be possible with a vanilla transformer architecture. Furthermore, we extend this approach to perform image-to-tree and point-cloud-to-tree conditional generation and to simulate the tree growth processes, generating 4D trees. Empirical results validate our approach in terms of speed, memory consumption, and generation quality.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 34 of its 74 references that are in the map. First posted on arXiv 7 Feb 2025.

Builds on

34 of 74 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2022Generative Adversarial Networkscited by 5,603
  6. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  7. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  8. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  9. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  10. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  11. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  12. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
22 more
  1. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  2. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  3. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  4. 2024GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generationcited by 151
  5. 2024MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformerscited by 140
  6. 2020LayoutTransformer: Layout Generation and Completion with Self-attentioncited by 122
  7. 2022SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebookscited by 121
  8. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 105
  9. 2024MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenizationcited by 102
  10. 2024MeshXL: Neural Coordinate Field for Generative 3D Foundation Modelscited by 100
  11. 2017Hierarchical Surface Prediction for 3D Object Reconstructioncited by 89
  12. 2024LLaMA-Mesh: Unifying 3D Mesh Generation with Language Modelscited by 87
  13. 2024Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scalecited by 87
  14. 2024EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generationcited by 84
  15. 2023IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformerscited by 73
  16. 2023PolyDiff: Generating 3D Polygonal Meshes with Diffusion Modelscited by 66
  17. 2019StructureNet: Hierarchical Graph Networks for 3D Shape Generationcited by 59
  18. 2021Engineering Sketch Generation for Computer-Aided Designcited by 49
  19. 2024PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidancecited by 47
  20. 2019StructEdit: Learning Structural Shape Variationscited by 23
  21. 2024LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusioncited by 16
  22. 2024Tree-D Fusion: Simulation-Ready Tree Dataset from Single Images with Diffusion Priorscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Demeter: A Parametric Model of Crop Plant Morphology from the Real Worldcited by 2
  2. 2026Grow with the Flow: 4D Reconstruction of Growing Plants with Gaussian Flow Fieldscited by 1
  3. 2026TreeSRNF: Square-Root Normal Fields for Generative Modelling of the Geometric and Structural Variability in Tree-like 3D Objectscited by 1