TY - GEN
T1 - 3D-PRNN
T2 - 16th IEEE International Conference on Computer Vision, ICCV 2017
AU - Zou, Chuhang
AU - Yumer, Ersin
AU - Yang, Jimei
AU - Ceylan, Duygu
AU - Hoiem, Derek
N1 - Funding Information:
This research is supported in part by NSF award 14-21521 and ONR MURI grant N00014-16-1-2007. We thank David Forsyth for insightful comments and discussion
Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/22
Y1 - 2017/12/22
N2 - The success of various applications including robotics, digital content creation, and visualization demand a structured and abstract representation of the 3D world from limited sensor data. Inspired by the nature of human perception of 3D shapes as a collection of simple parts, we explore such an abstract shape representation based on primitives. Given a single depth image of an object, we present 3DPRNN, a generative recurrent neural network that synthesizes multiple plausible shapes composed of a set of primitives. Our generative model encodes symmetry characteristics of common man-made objects, preserves long-range structural coherence, and describes objects of varying complexity with a compact representation. We also propose a method based on Gaussian Fields to generate a large scale dataset of primitive-based shape representations to train our network. We evaluate our approach on a wide range of examples and show that it outperforms nearest-neighbor based shape retrieval methods and is on-par with voxelbased generative models while using a significantly reduced parameter space.
AB - The success of various applications including robotics, digital content creation, and visualization demand a structured and abstract representation of the 3D world from limited sensor data. Inspired by the nature of human perception of 3D shapes as a collection of simple parts, we explore such an abstract shape representation based on primitives. Given a single depth image of an object, we present 3DPRNN, a generative recurrent neural network that synthesizes multiple plausible shapes composed of a set of primitives. Our generative model encodes symmetry characteristics of common man-made objects, preserves long-range structural coherence, and describes objects of varying complexity with a compact representation. We also propose a method based on Gaussian Fields to generate a large scale dataset of primitive-based shape representations to train our network. We evaluate our approach on a wide range of examples and show that it outperforms nearest-neighbor based shape retrieval methods and is on-par with voxelbased generative models while using a significantly reduced parameter space.
UR - http://www.scopus.com/inward/record.url?scp=85041917778&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85041917778&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2017.103
DO - 10.1109/ICCV.2017.103
M3 - Conference contribution
AN - SCOPUS:85041917778
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 900
EP - 909
BT - Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 22 October 2017 through 29 October 2017
ER -