Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching

Reconstruction of object or scene surfaces has tremendous applications in computer vision, computer graphics, and robotics. In this paper, we study a fundamental problem in this context about recovering a surface mesh from an implicit field function whose zero-level set captures the underlying surfa...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2021) vom: 14. Dez.
1. Verfasser: Lei, Jiabao (VerfasserIn)
Weitere Verfasser: Jia, Kui, Ma, Yi
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2021
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM334419115
003 DE-627
005 20250302191150.0
007 cr uuu---uuuuu
008 231225s2021 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2021.3135007  |2 doi 
028 5 2 |a pubmed25n1114.xml 
035 |a (DE-627)NLM334419115 
035 |a (NLM)34905490 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Lei, Jiabao  |e verfasserin  |4 aut 
245 1 0 |a Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching 
264 1 |c 2021 
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 20.02.2024 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a Reconstruction of object or scene surfaces has tremendous applications in computer vision, computer graphics, and robotics. In this paper, we study a fundamental problem in this context about recovering a surface mesh from an implicit field function whose zero-level set captures the underlying surface. Given that an MLP with activations of Rectified Linear Unit (ReLU) partitions its input space into a number of linear regions, we are motivated to connect this local linearity with a same property owned by the desired result of polygon mesh. More specifically, we identify from the linear regions, partitioned by an MLP based implicit function, the analytic cells and analytic faces that are associated with the function's zero-level isosurface. We prove that under mild conditions, the identified analytic faces are guaranteed to connect and form a closed, piecewise planar surface. Based on the theorem, we propose an algorithm of analytic marching, which marches among analytic cells to exactly recover the mesh captured by an implicit surface network. We also show that our theory and algorithm are equally applicable to advanced MLPs with shortcut connections and max pooling. Extensive experiments demonstrate our advantages over existing methods in terms of both meshing accuracy and efficiency 
650 4 |a Journal Article 
700 1 |a Jia, Kui  |e verfasserin  |4 aut 
700 1 |a Ma, Yi  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g PP(2021) vom: 14. Dez.  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:PP  |g year:2021  |g day:14  |g month:12 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2021.3135007  |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 2021  |b 14  |c 12