
UDiFF, a 3D diffusion model, can generate textured 3D shapes with open surfaces from text conditions or unconditionally by leveraging an optimal wavelet transformation for compact unsigned distance field representation.


coremsg

generating-diverse-3d-shapes-with-open-surfaces-using-conditional-unsigned-distance-field-diffusion


Generating Diverse 3D Shapes with Open Surfaces Using Conditional Unsigned Distance Field Diffusion


title_rewrite


Surf-D proposes a novel method for generating high-quality 3D shapes with arbitrary topologies using diffusion models, outperforming previous approaches.


surf-d-generating-high-quality-surfaces-of-arbitrary-topologies-using-diffusion-models


Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models



提案されたHyperSDFusionは、テキストから3D形状を生成する際に、ハイパーボリック空間での階層構造の学習を活用し、最先端の結果を達成します。


hypersdfusion-bridging-hierarchical-structures-in-language-and-geometry-for-enhanced-3d-text2shape-generation


HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation
