The Youtube video below possibly shows passive stereo 3D vision limitation - only high-contrast objects are visible on the depth map. Probably the flat panels of cubicles and walls do not have a sufficient contrast:
Seems like passive stereo would actually rely to some extent on flat/uniform areas. If the image was highly detailed throughout the cross-correlation would have a harder time. Finding a single edge in a uniform region isn't that hard.
Seems like passive stereo would actually rely to some extent on flat/uniform areas. If the image was highly detailed throughout the cross-correlation would have a harder time. Finding a single edge in a uniform region isn't that hard.
ReplyDelete