GenPoly : Learning Generalized and Tessellated Shape Priors via 3D Polymorphic Evolving

We introduce GenPoly, a novel generalized 3D prior model designed for multiple 3D generation tasks, focusing on preserving fine details. While previous works learn generalizable representations by decomposing objects into coarse-grained components to reassemble a coherent global structure, this appr...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2025) vom: 31. Juli
1. Verfasser: Liu, Bangzhen (VerfasserIn)
Weitere Verfasser: Yu, Yuyang, Xu, Xuemiao, Xu, Cheng, Zheng, Chenxi, Yang, Haoxin, Huang, Shaoyu, He, Shengfeng
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2025
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652c 4500
001 NLM390418242
003 DE-627
005 20250801233639.0
007 cr uuu---uuuuu
008 250801s2025 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2025.3593807  |2 doi 
028 5 2 |a pubmed25n1516.xml 
035 |a (DE-627)NLM390418242 
035 |a (NLM)40742856 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Liu, Bangzhen  |e verfasserin  |4 aut 
245 1 0 |a GenPoly  |b Learning Generalized and Tessellated Shape Priors via 3D Polymorphic Evolving 
264 1 |c 2025 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 31.07.2025 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a We introduce GenPoly, a novel generalized 3D prior model designed for multiple 3D generation tasks, focusing on preserving fine details. While previous works learn generalizable representations by decomposing objects into coarse-grained components to reassemble a coherent global structure, this approach sacrifices small-scale details. In this paper, we take a different perspective, formulating 3D prior modeling as a bottom-up polymorphic evolving process. Our key insight is that, beyond global structures, intricate local geometry variations hold rich contextual information that should be incorporated into the modeling process to learn fine-grained, generalizable representations. This allows coarse shapes to progressively evolve through multi-granular local geometry refinements, enabling high-fidelity 3D generation. To this end, we first introduce a polymorphic variational autoencoder (PolyVAE), which constructs a versatile shape residual codebook via a polymorphic quantization mechanism. This codebook strategically encodes intricate local geometry representations from tesselated shapes within the latent space. Building on these representations, a 3D polymorphic evolving scheme is further developed to refine local details in a coarse-to-fine manner progressively. In this way, visually compelling 3D shapes with rich and complex details can be ultimately generated. The effectiveness of our method is demonstrated through extensive qualitative and quantitative evaluations, where GenPoly consistently surpasses state-of-the-art methods across various downstream tasks, particularly in local detail preservation. The code and more visualizations will be available on our project website 
650 4 |a Journal Article 
700 1 |a Yu, Yuyang  |e verfasserin  |4 aut 
700 1 |a Xu, Xuemiao  |e verfasserin  |4 aut 
700 1 |a Xu, Cheng  |e verfasserin  |4 aut 
700 1 |a Zheng, Chenxi  |e verfasserin  |4 aut 
700 1 |a Yang, Haoxin  |e verfasserin  |4 aut 
700 1 |a Huang, Shaoyu  |e verfasserin  |4 aut 
700 1 |a He, Shengfeng  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g PP(2025) vom: 31. Juli  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:PP  |g year:2025  |g day:31  |g month:07 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2025.3593807  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d PP  |j 2025  |b 31  |c 07