File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TPAMI.2021.3135007
- Scopus: eid_2-s2.0-85121142534
- WOS: WOS:000880661400106
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching
Title | Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching |
---|---|
Authors | |
Keywords | deep learning Generative shape modeling implicit surface representation multi-layer perceptron polygon mesh |
Issue Date | 2022 |
Citation | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, v. 44, n. 12, p. 10068-10086 How to Cite? |
Abstract | Reconstruction of object or scene surfaces has tremendous applications in computer vision, computer graphics, and robotics. The topic attracts increased attention with the emerging pipeline of deep learning surface reconstruction, where implicit field functions constructed from deep networks (e.g., multi-layer perceptrons or MLPs) are proposed for generative shape modeling. 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. To achieve the goal, existing methods rely on traditional meshing algorithms (e.g., the de-facto standard marching cubes); while promising, they suffer from loss of precision learned in the implicit surface networks, due to the use of discrete space sampling in marching cubes. 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 facesthat 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. Given the parallel nature of analytic marching, we contribute AnalyticMesh, a software package that supports efficient meshing of implicit surface networks via CUDA parallel computing, and mesh simplification for efficient downstream processing. We apply our method to different settings of generative shape modeling using implicit surface networks. Extensive experiments demonstrate our advantages over existing methods in terms of both meshing accuracy and efficiency. Codes are at https://github.com/Karbo123/AnalyticMesh. |
Persistent Identifier | http://hdl.handle.net/10722/327778 |
ISSN | 2023 Impact Factor: 20.8 2023 SCImago Journal Rankings: 6.158 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lei, Jiabao | - |
dc.contributor.author | Jia, Kui | - |
dc.contributor.author | Ma, Yi | - |
dc.date.accessioned | 2023-05-08T02:26:44Z | - |
dc.date.available | 2023-05-08T02:26:44Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, v. 44, n. 12, p. 10068-10086 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.uri | http://hdl.handle.net/10722/327778 | - |
dc.description.abstract | Reconstruction of object or scene surfaces has tremendous applications in computer vision, computer graphics, and robotics. The topic attracts increased attention with the emerging pipeline of deep learning surface reconstruction, where implicit field functions constructed from deep networks (e.g., multi-layer perceptrons or MLPs) are proposed for generative shape modeling. 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. To achieve the goal, existing methods rely on traditional meshing algorithms (e.g., the de-facto standard marching cubes); while promising, they suffer from loss of precision learned in the implicit surface networks, due to the use of discrete space sampling in marching cubes. 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 facesthat 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. Given the parallel nature of analytic marching, we contribute AnalyticMesh, a software package that supports efficient meshing of implicit surface networks via CUDA parallel computing, and mesh simplification for efficient downstream processing. We apply our method to different settings of generative shape modeling using implicit surface networks. Extensive experiments demonstrate our advantages over existing methods in terms of both meshing accuracy and efficiency. Codes are at https://github.com/Karbo123/AnalyticMesh. | - |
dc.language | eng | - |
dc.relation.ispartof | IEEE Transactions on Pattern Analysis and Machine Intelligence | - |
dc.subject | deep learning | - |
dc.subject | Generative shape modeling | - |
dc.subject | implicit surface representation | - |
dc.subject | multi-layer perceptron | - |
dc.subject | polygon mesh | - |
dc.title | Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TPAMI.2021.3135007 | - |
dc.identifier.scopus | eid_2-s2.0-85121142534 | - |
dc.identifier.volume | 44 | - |
dc.identifier.issue | 12 | - |
dc.identifier.spage | 10068 | - |
dc.identifier.epage | 10086 | - |
dc.identifier.eissn | 1939-3539 | - |
dc.identifier.isi | WOS:000880661400106 | - |