scholarly journals Non-local Spatial Propagation Network for Depth Completion

2020 ◽  
pp. 120-136
Author(s):  
Jinsun Park ◽  
Kyungdon Joo ◽  
Zhe Hu ◽  
Chi-Kuei Liu ◽  
In So Kweon
Keyword(s):  
Spatial Propagation ◽  
Non Local ◽  
Propagation Network

scholarly journals Learning Depth with Convolutional Spatial Propagation Network

2020 ◽  
Vol 42 (10) ◽  
pp. 2361-2379 ◽  
Author(s):  
Xinjing Cheng ◽  
Peng Wang ◽  
Ruigang Yang
Keyword(s):  
Spatial Propagation ◽  
Propagation Network

scholarly journals CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion

2020 ◽  
Vol 34 (07) ◽  
pp. 10615-10622
Author(s):  
Xinjing Cheng ◽  
Peng Wang ◽  
Chenye Guan ◽  
Ruigang Yang
Keyword(s):  
Color Image ◽  
Depth Map ◽  
Computational Resource ◽  
Learning Context ◽  
Structural Details ◽  
Spatial Propagation ◽  
Effectiveness And Efficiency ◽  
Computational Budget ◽  
Propagation Network ◽  
Resource Aware

Depth Completion deals with the problem of converting a sparse depth map to a dense one, given the corresponding color image. Convolutional spatial propagation network (CSPN) is one of the state-of-the-art (SoTA) methods of depth completion, which recovers structural details of the scene. In this paper, we propose CSPN++, which further improves its effectiveness and efficiency by learning adaptive convolutional kernel sizes and the number of iterations for the propagation, thus the context and computational resource needed at each pixel could be dynamically assigned upon requests. Specifically, we formulate the learning of the two hyper-parameters as an architecture selection problem where various configurations of kernel sizes and numbers of iterations are first defined, and then a set of soft weighting parameters are trained to either properly assemble or select from the pre-defined configurations at each pixel. In our experiments, we find weighted assembling can lead to significant accuracy improvements, which we referred to as "context-aware CSPN", while weighted selection, "resource-aware CSPN" can reduce the computational resource significantly with similar or better accuracy. Besides, the resource needed for CSPN++ can be adjusted w.r.t. the computational budget automatically. Finally, to avoid the side effects of noise or inaccurate sparse depths, we embed a gated network inside CSPN++, which further improves the performance. We demonstrate the effectiveness of CSPN++ on the KITTI depth completion benchmark, where it significantly improves over CSPN and other SoTA methods 1.

Toward High-Resolution Low-Voltage SEM

1988 ◽  
Vol 46 ◽  
pp. 218-219
Author(s):  
Zhifeng Shao
Keyword(s):  
Low Voltage ◽  
Spherical Aberration ◽  
Chromatic Aberration ◽  
Limiting Factor ◽  
Operating Voltage ◽  
Probe Radius ◽  
Non Local ◽  
Electron Microscopes ◽  
Image Position ◽  
Scanning Electron Microscopes

Recently, low voltage (≤5kV) scanning electron microscopes have become popular because of their unprecedented advantages, such as minimized charging effects and smaller specimen damage, etc. Perhaps the most important advantage of LVSEM is that they may be able to provide ultrahigh resolution since the interaction volume decreases when electron energy is reduced. It is obvious that no matter how low the operating voltage is, the resolution is always poorer than the probe radius. To achieve 10Å resolution at 5kV (including non-local effects), we would require a probe radius of 5∽6 Å. At low voltages, we can no longer ignore the effects of chromatic aberration because of the increased ratio δV/V. The 3rd order spherical aberration is another major limiting factor. The optimized aperture should be calculated as

Chromatic aberration and low-voltage SEM

1987 ◽  
Vol 45 ◽  
pp. 546-547
Author(s):  
Zhifeng Shao ◽  
A.V. Crewe
Keyword(s):  
Electron Energy ◽  
Low Voltage ◽  
Spherical Aberration ◽  
Chromatic Aberration ◽  
Primary Electron ◽  
Probe Size ◽  
Non Local ◽  
Optical Treatment ◽  
Electron Microscopes ◽  
Scanning Electron Microscopes

For scanning electron microscopes, it is plausible that by lowering the primary electron energy, one can decrease the volume of interaction and improve resolution. As shown by Crewe /1/, at V0 =5kV a 10Å resolution (including non-local effects) is possible. To achieve this, we would need a probe size about 5Å. However, at low voltages, the chromatic aberration becomes the major concern even for field emission sources. In this case, δV/V = 0.1 V/5kV = 2x10-5. As a rough estimate, it has been shown that /2/ the chromatic aberration δC should be less than ⅓ of δ0 the probe size determined by diffraction and spherical aberration in order to neglect its effect. But this did not take into account the distribution of electron energy. We will show that by using a wave optical treatment, the tolerance on the chromatic aberration is much larger than we expected.

Magic of signs: a non-local interpretation of homeopathy

2000 ◽  
Vol 89 (3) ◽  
pp. 127-140 ◽  
Author(s):  
H Walach
Keyword(s):  
Non Local
Sign in / Sign up

Export Citation Format

Share Document