|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM314437908 |
| 003 |
DE-627 |
| 005 |
20231225152732.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2022 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2020.3020800
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1048.xml
|
| 035 |
|
|
|a (DE-627)NLM314437908
|
| 035 |
|
|
|a (NLM)32870785
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Qi, Xiaojuan
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a GeoNet++
|b Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation
|
| 264 |
|
1 |
|c 2022
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 28.03.2022
|
| 500 |
|
|
|a Date Revised 01.04.2022
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status MEDLINE
|
| 520 |
|
|
|a In this paper, we propose a geometric neural network with edge-aware refinement (GeoNet++) to jointly predict both depth and surface normal maps from a single image. Building on top of two-stream CNNs, GeoNet++ captures the geometric relationships between depth and surface normals with the proposed depth-to-normal and normal-to-depth modules. In particular, the "depth-to-normal" module exploits the least square solution of estimating surface normals from depth to improve their quality, while the "normal-to-depth" module refines the depth map based on the constraints on surface normals through kernel regression. Boundary information is exploited via an edge-aware refinement module. GeoNet++ effectively predicts depth and surface normals with high 3D consistency and sharp boundaries resulting in better reconstructed 3D scenes. Note that GeoNet++ is generic and can be used in other depth/normal prediction frameworks to improve 3D reconstruction quality and pixel-wise accuracy of depth and surface normals. Furthermore, we propose a new 3D geometric metric (3DGM) for evaluating depth prediction in 3D. In contrast to current metrics that focus on evaluating pixel-wise error/accuracy, 3DGM measures whether the predicted depth can reconstruct high quality 3D surface normals. This is a more natural metric for many 3D application domains. Our experiments on NYUD-V2 [1] and KITTI [2] datasets verify that GeoNet++ produces fine boundary details and the predicted depth can be used to reconstruct high quality 3D surfaces
|
| 650 |
|
4 |
|a Journal Article
|
| 650 |
|
4 |
|a Research Support, Non-U.S. Gov't
|
| 700 |
1 |
|
|a Liu, Zhengzhe
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liao, Renjie
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Torr, Philip H S
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Urtasun, Raquel
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Jia, Jiaya
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 44(2022), 2 vom: 01. Feb., Seite 969-984
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:44
|g year:2022
|g number:2
|g day:01
|g month:02
|g pages:969-984
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2020.3020800
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 44
|j 2022
|e 2
|b 01
|c 02
|h 969-984
|