mlsanityData to 7 Oct 2026

FreeMesh: Boosting Mesh Generation with Coordinates Merging

arXiv 2505.13573 ↗First posted 19 May 2025cs.GR cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

The next-coordinate prediction paradigm has emerged as the de facto standard in current auto-regressive mesh generation methods. Despite their effectiveness, there is no efficient measurement for the various tokenizers that serialize meshes into sequences. In this paper, we introduce a new metric Per-Token-Mesh-Entropy (PTME) to evaluate the existing mesh tokenizers theoretically without any training. Building upon PTME, we propose a plug-and-play tokenization technique called coordinate merging. It further improves the compression ratios of existing tokenizers by rearranging and merging the most frequent patterns of coordinates. Through experiments on various tokenization methods like MeshXL, MeshAnything V2, and Edgerunner, we further validate the performance of our method. We hope that the proposed PTME and coordinate merging can enhance the existing mesh tokenizers and guide the further development of native mesh generation.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 33 of its 38 references that are in the map. First posted on arXiv 19 May 2025.

Builds on

33 of 38 references.

References · 33

  1. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  4. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  5. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  6. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  7. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 837
  8. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  9. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  10. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
  11. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  12. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
21 more
  1. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 421
  2. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
  3. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 306
  4. 2023Text-to-3D using Gaussian Splattingcited by 299
  5. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 254
  6. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 225
  7. 2018Character-Level Language Modeling with Deeper Self-Attentioncited by 138
  8. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 138
  9. 2024Byte Latent Transformer: Patches Scale Better Than Tokenscited by 137
  10. 2023Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Modelscited by 122
  11. 2024MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenizationcited by 102
  12. 2024MeshXL: Neural Coordinate Field for Generative 3D Foundation Modelscited by 100
  13. 20243DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusioncited by 100
  14. 2024MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstructioncited by 94
  15. 2024Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scalecited by 87
  16. 2024EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generationcited by 84
  17. 2024Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generationcited by 82
  18. 2024Scaling Mesh Generation via Compressive Tokenizationcited by 71
  19. 2020Vocabulary Learning via Optimal Transport for Neural Machine Translationcited by 58
  20. 2024PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidancecited by 47
  21. 2024DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesioncited by 60
  2. 2025ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understandingcited by 34
  3. 2026FACE: A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh Generationcited by 4
  4. 2026Mesh-Pro: Asynchronous Advantage-guided Ranking Preference Optimization for Artist-style Quadrilateral Mesh Generationcited by 2
  5. 2026Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modelingcited by 1
  6. 2026TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generationcited by 0