Temporal Shape Super-Resolution by Intra-frame Motion Encoding Using High-fps Structured Light

@article{Shiba2017TemporalSS,
  title={Temporal Shape Super-Resolution by Intra-frame Motion Encoding Using High-fps Structured Light},
  author={Yuki Shiba and Satoshi Ono and Ryo Furukawa and Shinsaku Hiura and Hiroshi Kawasaki},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={115-123}
}
  • Yuki Shiba, S. Ono, H. Kawasaki
  • Published 2 October 2017
  • Computer Science
  • 2017 IEEE International Conference on Computer Vision (ICCV)
One of the solutions of depth imaging of moving scene is to project a static pattern on the object and use just a single image for reconstruction. However, if the motion of the object is too fast with respect to the exposure time of the image sensor, patterns on the captured image are blurred and reconstruction fails. In this paper, we impose multiple projection patterns into each single captured image to realize temporal super resolution of the depth image sequences. With our method, multiple… 
Temporal super-resolution microscopy using a hue-encoded shutter C
TLDR
This paper proposes an approach to extend the temporal resolution of a conventional digital color camera by leveraging a multi-color illumination source by trading spectral for temporal information and allows rapid switching to standard RGB acquisition.
Active illumination and computational Methods for Temporal and Spectral Super-Resolution Microscopy
TLDR
This thesis presents methods based on the use of active illumination and computational algorithms to increase temporal and spectral resolutions of microscopes and has fundamental implications on the signal sensing procedure, allowing, for example, to mitigate temporal aliasing in sequences of images.
Design of Chinese Character Coded Targets for Feature Point Recognition Under Motion-Blur Effect
TLDR
A set of novel Chinese character coded targets (CCTs) are designed and tested and a Faster Region-based Convolutional Neural Network (Faster R-CNN) is trained to locate and recognize the CCTs in motion blurred images.

References

SHOWING 1-10 OF 28 REFERENCES
Motion-Aware Structured Light Using Spatio-Temporal Decodable Patterns
TLDR
A structured light system using a sequence of shifted stripe patterns that is decodable both spatially and temporally that enables motion-aware reconstruction for each pixel and significantly reduces the number of pixels around discontinuities where depth cannot be recovered in traditional approaches.
Dense one-shot 3D reconstruction by detecting continuous regions with parallel line projection
TLDR
The linear solution to eliminate the DOF by using geometric informations of the devices, i.e. epipolar constraint is presented and the accuracy of correspondences is evaluated and the comparison with respect to the number of projectors by simulation.
Video from a single coded exposure photograph using a learned over-complete dictionary
TLDR
It is shown that the proposed techniques for sampling, representing and reconstructing the space-time volume can effectively reconstruct a video from a single image maintaining high spatial resolution.
Active One-Shot Scan for Wide Depth Range Using a Light Field Projector Based on Coded Aperture
TLDR
An image-based approach is proposed to apply a stereo technique to the system and it is confirmed that the method can accurately recover the dense shape of curved and textured objects for a wide range of depths from a single captured image.
Space-time super-resolution
TLDR
A method for constructing a video sequence of high space-time resolution by combining information from multiple low-resolution video sequences of the same dynamic scene by recovering rapid dynamic events that occur faster than regular frame-rate is proposed.
HyperDepth: Learning Depth from Structured Light without Matching
TLDR
The algorithmic performance is demonstrated, creating high resolution real-time depth maps that surpass the quality of current state of the art depth technologies, highlighting quantization-free results with reduced holes, edge fattening and other stereo-based depth artifacts.
One-shot scanning using De Bruijn spaced grids
TLDR
This paper presents an efficient one-shot method which exploits simple geometric constraints to solve the correspondence problem, and introduces De Bruijn spaced grids, a novel grid pattern, which is much more robust compared to those based on uniform spaced grids.
High-speed imaging using CMOS image sensor with quasi pixel-wise exposure
TLDR
This work fabricated a prototype complementary metal oxide semiconductor (CMOS) image sensor with quasi pixel-wise exposure timing that can realize nonuniform space-time sampling and reconstructs the high-speed video sequence from the images produced by pseudo-random sampling using an over-complete dictionary.
P2C2: Programmable pixel compressive camera for high speed imaging
TLDR
By modeling such spatio-temporal redundancies in a video volume, one can faithfully recover the underlying high-speed video frames from the observed low speed coded video by proposing a reconstruction algorithm that uses the data from P2C2 along with additional priors about videos to perform temporal super-resolution.
Enhancing and experiencing spacetime resolution with videos and stills
TLDR
The framework enables a variety of applications that were previously unavailable to the amateur user, such as the ability to automatically create videos with high spatiotemporal resolution, and shift a high-resolution still to nearby points in time to better capture a missed event.
...
...