Temporal shape super-resolution by intra-frame motion encoding using high-fps structured light
Previous work on one-shot scene-capture used single captured image in order to get a single shape.
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.
if the scene motion is fast with projector-camera system , motion blur decreases in our projection, and not only a single shape,
but also sequential shapes can be recovered; we call this temporal shape super-resolution.
Temporal shape super-resolution
System configuration.
The basic theory of temporal shape super-resolution.
We impose multiple projection patterns into each single captured image to realize temporal super resolution of the depth image sequences.
With our method, multiple patterns are projected onto the object with higher fps than possible with a camera.
In this case, the observed pattern varies depending on the depth and motion of the object, so we can extract temporal information of the scene from each single image.
Shiba Yuki, Satoshi Ono, Ryo Furukawa, Shinsaku Hiura, Hiroshi Kawasaki,
"Intra-frame motion encoding using high-fps structured light for temporal shape super-resolution"
The proceedings of the 20th Meeting on Image and Recognition and Understanding (MIRU2017) Oral presentation, 4pages, 8.2017,
Encouragement Award for Student
