p105fig03.22 Depth-selective boundary representations capture brightness and colors in surface filling-in domains.  See the text for details.<BR>|| 3D vision and figure-ground separation.  multiple-scale, depth-selective boundary webs. refer to <A HREF="images- Grossberg 2021/p104fig03.21 Four examples of how emergent boundaries can form in response to different kinds of images.png">Figure 3.21(d)</a><TABLE border="1"><TR><TD><B>depth increasing ↓</td><TD><B>boundaries</td><TD><B>surfaces</td></tr><TR><TD></td><TD>BC input</td><TD>surface capture!</td></tr><TR><TD></td><TD>FC input</td><TD></td></tr></table>