PGT-NeuS : Progressive-Growing Tri-Plane Representation for Neural Surface Reconstruction

3D reconstruction from multi-view images is a long-standing problem in computer graphic. Neural 3D reconstruction, especially NeuS and its variants, has improved reconstruction quality compared to traditional methods. However, it is still a challenge for these methods to reconstruct fine-grained geo...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on visualization and computer graphics. - 1996. - 31(2025), 10 vom: 25. Sept., Seite 9213-9224
1. Verfasser: Xiang, Xue-Kun (VerfasserIn)
Weitere Verfasser: Yuan, Yu-Jie, Hu, Wen-Bo, Liu, Yu-Tao, Ma, Yue-Wen, Gao, Lin
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2025
Zugriff auf das übergeordnete Werk:IEEE transactions on visualization and computer graphics
Schlagworte:Journal Article
LEADER 01000naa a22002652c 4500
001 NLM392025388
003 DE-627
005 20250906233729.0
007 cr uuu---uuuuu
008 250906s2025 xx |||||o 00| ||eng c
024 7 |a 10.1109/TVCG.2025.3590394  |2 doi 
028 5 2 |a pubmed25n1558.xml 
035 |a (DE-627)NLM392025388 
035 |a (NLM)40711905 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Xiang, Xue-Kun  |e verfasserin  |4 aut 
245 1 0 |a PGT-NeuS  |b Progressive-Growing Tri-Plane Representation for Neural Surface Reconstruction 
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 05.09.2025 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a 3D reconstruction from multi-view images is a long-standing problem in computer graphic. Neural 3D reconstruction, especially NeuS and its variants, has improved reconstruction quality compared to traditional methods. However, it is still a challenge for these methods to reconstruct fine-grained geometric details since the spherical harmonic positional encoding lacks the ability to express high-frequency signals. In this paper, we propose a multi-resolution tri-plane feature encoding that leverages the detail reconstruction capabilities of high-resolution tri-plane while using the smoothness of low-resolution tri-plane to suppress high-frequency artifacts. Additionally, a progressive training strategy is introduced, gradually merging scene details from coarse to fine granularity, enhancing reconstruction quality while maintaining training stability and reducing difficulty. Furthermore, to address reconstruction challenges arising from sparse viewpoints and inconsistent lighting in image datasets, we introduce normal priors as supervision and propose consistency verification for multi-view normal priors, which assesses the accuracy of normal priors and effectively supervise the reconstructed surfaces. Moreover, we propose a perturbing and fine-tuning strategy on regions of unreliable normal priors to further improve the quality of geometric surface reconstruction 
650 4 |a Journal Article 
700 1 |a Yuan, Yu-Jie  |e verfasserin  |4 aut 
700 1 |a Hu, Wen-Bo  |e verfasserin  |4 aut 
700 1 |a Liu, Yu-Tao  |e verfasserin  |4 aut 
700 1 |a Ma, Yue-Wen  |e verfasserin  |4 aut 
700 1 |a Gao, Lin  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on visualization and computer graphics  |d 1996  |g 31(2025), 10 vom: 25. Sept., Seite 9213-9224  |w (DE-627)NLM098269445  |x 1941-0506  |7 nnas 
773 1 8 |g volume:31  |g year:2025  |g number:10  |g day:25  |g month:09  |g pages:9213-9224 
856 4 0 |u http://dx.doi.org/10.1109/TVCG.2025.3590394  |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 31  |j 2025  |e 10  |b 25  |c 09  |h 9213-9224