scholarly journals Auto Coloring with Enhanced Character Registration

2008 ◽  
Vol 2008 ◽  
pp. 1-7 ◽  
Author(s):  
Jie Qiu ◽  
Hock Soon Seah ◽  
Feng Tian ◽  
Quan Chen ◽  
Zhongke Wu ◽  
...  
Keyword(s):  
Reference Frame ◽  
Registration Method ◽  
Stable Branch ◽  
2D Animation ◽  
Target Frame

An enhanced character registration method is proposed in this paper to assist the auto coloring for 2D animation characters. After skeletons are extracted, the skeleton of the character in a target frame is relocated based on a stable branch in a reference frame. Subsequently the characters among a sequence are automatically matched and registered. Occlusion are then detected and located in certain components segmented from the character. Two different approaches are applied to color regions in components without and with occlusion respectively. The approach has been tested for coloring a practical animation sequence and achieved high coloring accuracy, showing its applicability in commercial animation production.

scholarly journals Temporal Adaptive Alignment Network for Deep Video Inpainting

2020 ◽  
Author(s):  
Ruixin Liu ◽  
Zhenyu Weng ◽  
Yuesheng Zhu ◽  
Bairong Li
Keyword(s):  
Deep Learning ◽  
Motion Estimation ◽  
Optical Flow ◽  
Reference Frame ◽  
Reference Frames ◽  
Qualitative Evaluation ◽  
Temporal Information ◽  
Temporal Alignment ◽  
Video Inpainting ◽  
Target Frame

Video inpainting aims to synthesize visually pleasant and temporally consistent content in missing regions of video. Due to a variety of motions across different frames, it is highly challenging to utilize effective temporal information to recover videos. Existing deep learning based methods usually estimate optical flow to align frames and thereby exploit useful information between frames. However, these methods tend to generate artifacts once the estimated optical flow is inaccurate. To alleviate above problem, we propose a novel end-to-end Temporal Adaptive Alignment Network(TAAN) for video inpainting. The TAAN aligns reference frames with target frame via implicit motion estimation at a feature level and then reconstruct target frame by taking the aggregated aligned reference frame features as input. In the proposed network, a Temporal Adaptive Alignment (TAA) module based on deformable convolutions is designed to perform temporal alignment in a local, dense and adaptive manner. Both quantitative and qualitative evaluation results show that our method significantly outperforms existing deep learning based methods.

scholarly journals Some Remarks on Registration Techniques of Point Clouds Obtained from Terrestrial Laser Scanning

2021 ◽  
Vol 906 (1) ◽  
pp. 012078
Author(s):  
Zbigniew Muszyński ◽  
Paulina Kujawa
Keyword(s):  
Reference Frame ◽  
Laser Scanning ◽  
Laser Scanner ◽  
Terrestrial Laser Scanning ◽  
Point Clouds ◽  
Engineering Structures ◽  
Registration Method ◽  
Railway Line ◽  
Local Reference ◽  
High Level

Abstract Terrestrial laser scanning (TLS) is a measurement technique used for many geodetic applications (such as determination of displacement and deformation of building objects or monitoring of engineering structures) as well as for non-geodetic applications (for example in forestry, archeology or geotechnics). Despite the high level of automation, the measurement with a laser scanner and the processing of the results consist of many stages and depend on many factors. The most important factors are: the features of measurement object (size, material, availability), required accuracy, speed of scanning, required scan density, type of reference frame, registration method, planned visualization, and 3D modelling method. In this article, the authors focused on the type of registration technique of point clouds obtained from TLS. The most popular strategies of registration were discussed. The practical application of the selected technique was presented on the example of measurement of the railway gauge of the viaduct. Due to the characteristic object (narrow and long railway line) and considering the local reference frame of point clouds as well as the need of minimization of the measurement time, the hybrid registration method in the nested variant was selected.

Practical Realization of a Reference System for Earth Dynamics by Satellite Methods

1975 ◽  
Vol 26 ◽  
pp. 341-380 ◽  
Author(s):  
R. J. Anderle ◽  
M. C. Tanenbaum
Keyword(s):  
Reference Frame ◽  
Polar Motion ◽  
Pole Position ◽  
Control Points ◽  
Significant Information ◽  
Crustal Motion ◽  
Average Reference ◽  
Future Data ◽  
Existing Data

AbstractObservations of artificial earth satellites provide a means of establishing an.origin, orientation, scale and control points for a coordinate system. Neither existing data nor future data are likely to provide significant information on the .001 angle between the axis of angular momentum and axis of rotation. Existing data have provided data to about .01 accuracy on the pole position and to possibly a meter on the origin of the system and for control points. The longitude origin is essentially arbitrary. While these accuracies permit acquisition of useful data on tides and polar motion through dynamio analyses, they are inadequate for determination of crustal motion or significant improvement in polar motion. The limitations arise from gravity, drag and radiation forces on the satellites as well as from instrument errors. Improvements in laser equipment and the launch of the dense LAGEOS satellite in an orbit high enough to suppress significant gravity and drag errors will permit determination of crustal motion and more accurate, higher frequency, polar motion. However, the reference frame for the results is likely to be an average reference frame defined by the observing stations, resulting in significant corrections to be determined for effects of changes in station configuration and data losses.

How Do Task Instructions Alter the Spatial Reference Frame of Scene-Based Processing?

2011 ◽  
Author(s):  
Mark Mills ◽  
Stefan Van Der Stigchel ◽  
Andrew Hollingworth ◽  
Michael D. Dodd
Keyword(s):  
Reference Frame ◽  
Spatial Reference ◽  
Task Instructions ◽  
Spatial Reference Frame

Astrometric measurement and reduction of Pulkovo photographic observations of the main Saturnian satellites from 1972 to 2007 in the Gaia reference frame

2020 ◽  
Author(s):  
M.Yu. Khovritchev ◽  
V. Robert ◽  
N.V. Narizhnaya ◽  
T.A. Vasilyeva ◽  
A.A. Apetyan ◽  
...  
Keyword(s):  
Reference Frame
Sign in / Sign up

Export Citation Format

Share Document