Context-guided depth completion via deep learning = 영상 정보를 이용한 심층학습 기반 깊이 정보 완성법

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 18
  • Download : 0
In this thesis, we present an end-to-end convolutional neural network (CNN) for depth completion. We aim to solve to major issues for effective depth completion. The first issue is to properly propagate the input depth samples. The second issue is to perform proper refinement of the initially propagated dense depth map. Our corresponding network consists of a geometry network, a convolutional spatial propagation network, and a context network. The geometry network, a single encoder-decoder network, learns to optimize a multi-task loss to generate an initial propagated depth map and a surface normal. The complementary outputs allow it to correctly propagate initial sparse depth points in slanted surfaces. The convolutional spatial propagation network learns the 8-way propagation affinity weights for better propagation from the input depth samples. The context network extracts a local and a global feature of an image to compute a bilateral weight, which enables it to preserve edges and fine details in the depth maps. We revisit and apply the traditional weighted median filter, with using the bilateral weight learnt from the context network. In order to validate the effectiveness and the robustness of our network, we performed extensive ablation studies and compared the results against state-of-the-art CNN-based depth completions, where we showed promising results on various scenes.
Advisors
Kweon, In Soresearcher권인소researcher
Description
한국과학기술원 :전기및전자공학부,
Publisher
한국과학기술원
Issue Date
2019
Identifier
325007
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2019.2,[iv, 27 p. :]

Keywords

Depth completion▼adepth estimation▼adeep learning▼aimage-guided filtering▼aweighted median filter; 깊이 정보 완성법▼a깊이 정보 추정▼a심층학습▼a영상 정보 기반 필터링▼a무게 중간값 필터

URI
http://hdl.handle.net/10203/266707
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=843410&flag=dissertation
Appears in Collection
EE-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0