File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/978-3-030-58607-2_32
- Scopus: eid_2-s2.0-85097386074
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Modeling 3D Shapes by Reinforcement Learning
Title | Modeling 3D Shapes by Reinforcement Learning |
---|---|
Authors | |
Issue Date | 2020 |
Publisher | Springer. The Proceedings' web site is located at https://link.springer.com/conference/eccv |
Citation | Proceedings of the 16th European Conference on Computer Vision (ECCV), Online, Glasgow, UK, 23-28 August 2020, pt X, p. 545-561 How to Cite? |
Abstract | We explore how to enable machines to model 3D shapes like human modelers using deep reinforcement learning (RL). In 3D modeling software like Maya, a modeler usually creates a mesh model in two steps: (1) approximating the shape using a set of primitives; (2) editing the meshes of the primitives to create detailed geometry. Inspired by such artist-based modeling, we propose a two-step neural framework based on RL to learn 3D modeling policies. By taking actions and collecting rewards in an interactive environment, the agents first learn to parse a target shape into primitives and then to edit the geometry. To effectively train the modeling agents, we introduce a novel training algorithm that combines heuristic policy, imitation learning and reinforcement learning. Our experiments show that the agents can learn good policies to produce regular and structure-aware mesh models, which demonstrates the feasibility and effectiveness of the proposed RL framework . |
Persistent Identifier | http://hdl.handle.net/10722/289180 |
ISBN | |
Series/Report no. | Lecture Notes in Computer Science (LNCS), v. 12355 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lin, C | - |
dc.contributor.author | Fan, TT | - |
dc.contributor.author | Wang, WP | - |
dc.contributor.author | Nießner, M | - |
dc.date.accessioned | 2020-10-22T08:08:58Z | - |
dc.date.available | 2020-10-22T08:08:58Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | Proceedings of the 16th European Conference on Computer Vision (ECCV), Online, Glasgow, UK, 23-28 August 2020, pt X, p. 545-561 | - |
dc.identifier.isbn | 9783030586065 | - |
dc.identifier.uri | http://hdl.handle.net/10722/289180 | - |
dc.description.abstract | We explore how to enable machines to model 3D shapes like human modelers using deep reinforcement learning (RL). In 3D modeling software like Maya, a modeler usually creates a mesh model in two steps: (1) approximating the shape using a set of primitives; (2) editing the meshes of the primitives to create detailed geometry. Inspired by such artist-based modeling, we propose a two-step neural framework based on RL to learn 3D modeling policies. By taking actions and collecting rewards in an interactive environment, the agents first learn to parse a target shape into primitives and then to edit the geometry. To effectively train the modeling agents, we introduce a novel training algorithm that combines heuristic policy, imitation learning and reinforcement learning. Our experiments show that the agents can learn good policies to produce regular and structure-aware mesh models, which demonstrates the feasibility and effectiveness of the proposed RL framework . | - |
dc.language | eng | - |
dc.publisher | Springer. The Proceedings' web site is located at https://link.springer.com/conference/eccv | - |
dc.relation.ispartof | Proceedings of the European Conference on Computer Vision (ECCV) | - |
dc.relation.ispartofseries | Lecture Notes in Computer Science (LNCS), v. 12355 | - |
dc.title | Modeling 3D Shapes by Reinforcement Learning | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Wang, WP: wenping@cs.hku.hk | - |
dc.identifier.authority | Wang, WP=rp00186 | - |
dc.identifier.doi | 10.1007/978-3-030-58607-2_32 | - |
dc.identifier.scopus | eid_2-s2.0-85097386074 | - |
dc.identifier.hkuros | 317158 | - |
dc.identifier.volume | X | - |
dc.identifier.spage | 545 | - |
dc.identifier.epage | 561 | - |
dc.publisher.place | Cham | - |