mlsanityData to 14 Oct 2026

Appearance-Preserving Refinement of Generated 3D Assets for Monochromatic Fabrication

arXiv 2606.26850 ↗First posted 25 Jun 2026cs.GR cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent advances in 3D mesh generation have enabled the creation of visually realistic assets. However, much of their visual fidelity is encoded in textures rather than geometry. When such assets are fabricated using monochromatic materials, texture information is largely lost, causing visually important details to disappear even when the original geometry is faithfully preserved. A key challenge is that the geometric perturbations required to recover texture-dependent appearance cues often introduce sharp local features and high-frequency surface structures, which may increase stress concentration and fabrication risk. In this paper, we present GenMF, an appearance-oriented geometry refinement framework for monochromatic fabrication. GenMF transforms texture-dependent visual cues into geometry-induced shading effects and formulates geometry refinement as a balance between appearance preservation and fabrication-oriented robustness. To discourage structurally and narrow the gap between simulation and physical manufacturing, we further introduce a differentiable stress-aware regularization based on a learned thermal-stress predictor. Experimental results demonstrate that GenMF significantly improves appearance preservation under monochromatic rendering while reducing stress concentration under a consistent thermo-mechanical simulation setting. Physical 3D printing examples further show that the refined geometries preserve more recognizable visual details while remaining suitable for fabrication. These results suggest that appearance-aware geometry refinement provides an effective bridge between generated 3D assets and fabrication-ready monochromatic objects.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 62 references that are in the map. First posted on arXiv 25 Jun 2026.

Builds on

35 of 62 references.

References · 35

  1. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  2. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  3. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
  4. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  5. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  6. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 938
  7. 2020Learning Mesh-Based Simulation with Graph Networkscited by 868
  8. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  9. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  10. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  11. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 689
  12. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 687
23 more
  1. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  2. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 433
  3. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 397
  4. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 343
  5. 2023GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Modelscited by 255
  6. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformercited by 210
  7. 2023TextMesh: Generation of Realistic 3D Meshes From Text Promptscited by 135
  8. 2022HF-NeuS: Improved Surface Reconstruction Using High-Frequency Detailscited by 121
  9. 2025Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attentioncited by 110
  10. 2025Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridgingcited by 99
  11. 2024LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generationcited by 92
  12. 2025PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformerscited by 84
  13. 2021Geometry-Consistent Neural Shape Representation with Implicit Displacement Fieldscited by 60
  14. 2024MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Modelcited by 55
  15. 2020Deep Geometric Texture Synthesiscited by 51
  16. 2020D2IM-Net: Learning Detail Disentangled Implicit Fields from Single Imagescited by 42
  17. 2023Novel DeepONet architecture to predict stresses in elastoplastic structures with variable complex geometries and loadscited by 33
  18. 2021Stress field prediction in fiber-reinforced composite materials using a deep learning approachcited by 23
  19. 2024IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminationscited by 22
  20. 2026MeshGraphNet-Transformer: Scalable Mesh-based Learned Simulation for Solid Mechanicscited by 10
  21. 2024Fancy123: One Image to High-Quality 3D Mesh Generation via Plug-and-Play Deformationcited by 7
  22. 2022Physics Informed Neural Network for Dynamic Stress Predictioncited by 6
  23. 2024Stress Predictions in Polycrystal Plasticity using Graph Neural Networks with Subgraph Trainingcited by 2

Built on by

Not cited yet.