6. Deep Learning研究はスピード勝負の時代。。。
6
CVPR2019で同じ「新しいコンセプト」の論文が3本
Learning Implicit Fields for Generative Shape Modeling
Zhiqin Chen, and Hao Zhang (Simon Fraser University)
published in arXiv on 2018/12/06
Occupancy Networks: Learning 3D Reconstruction in Function
Space
Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowzin,
and Andreas Geiger (University ofTubingen, ETAS GmbH, Stuttgart,
Google AI Berlin)
published in arXiv on 2018/12/10
7. Deep Learning研究はスピード勝負の時代。。。
7
CVPR2019で同じ「新しいコンセプト」の論文が3本
Learning Implicit Fields for Generative Shape Modeling
Zhiqin Chen, and Hao Zhang (Simon Fraser University)
published in arXiv on 2018/12/06
Occupancy Networks: Learning 3D Reconstruction in Function
Space
Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowzin,
and Andreas Geiger (University ofTubingen, ETAS GmbH, Stuttgart,
Google AI Berlin)
published in arXiv on 2018/12/10
DeepSDF: Learning Continuous Signed Distance Functions for Shape
Representation
Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe,
Steven Lovegrove (University ofWashington, MIT, Facebook Reality Labs)
published in arXiv on 2019/01/16
8. 本日の発表
8
CVPR2019で発表された「Deep Learningを使って
3Dモデルを表現する」論文を3本紹介
IM-NET
Learning Implicit Fields for Generative Shape Modeling
Occupancy Networks
Occupancy Networks: Learning 3D Reconstruction in
Function Space
DeepSDF
DeepSDF: Learning Continuous Signed Distance
Functions for Shape Representation
9. 3D Shapeの表現
9
Figure from “Occupancy Networks: Learning 3D Reconstruction in Function Space”
Voxel Point Cloud Mesh
+Simple
-Cubic Memory
-Manhattan world
+Fast and Easy
-No connectivity
-Lossy Postprocessing
+Natural
-Require Template
(topology)
-Self-intersections
10. 3D Shapeの表現
10
Voxel Point Cloud Mesh Deep Learning
+Infinite Resolution
+Arbitrary Topologies
+Watertight Meshes
Figure from “Occupancy Networks: Learning 3D Reconstruction in Function Space”
+Simple
-Cubic Memory
-Manhattan world
+Fast and Easy
-No connectivity
-Lossy Postprocessing
+Natural
-Require Template
(topology)
-Self-intersections