Making a Machine that Sees Like UsMaking a Machine That Sees Like Us explains why and how our visual perceptions can provide us with an accurate representation of the external world. Along the way, it tells the story of a machine (a computational model) built by the authors that solves the computationally difficult problem of seeing the way humans do. This accomplishment required a radical paradigm shift - one that challenged preconceptions about visual perception and tested the limits of human behavior-modeling for practical application. The text balances scientific sophistication and compelling storytelling, making it accessible to both technical and general readers. Online demonstrations and references to the authors' previously published papers detail how the machine was developed and what drove the ideas needed to make it work. The authors contextualize their new theory of shape perception by highlighting criticisms and opposing theories, offering readers a fascinating account not only of their revolutionary results, but of the scientific process that guided the way. |
Contents
1 How the Stage Was Set When We Began | 1 |
2 How This All Got Started | 52 |
3 Symmetry in Vision Inside and Outside of the Laboratory | 83 |
4 Using Symmetry is Not Simple | 120 |
5 A Second View Makes 3D Shape Perception Perfect | 144 |
6 Figureground Organization Which Breaks Camouflage in Everyday Life Permits the Veridical Recovery of a 3D Scene | 172 |
7 What Made This Possible and What Comes Next? | 204 |
Note Added in Proofs | 221 |
| 229 | |
| 237 | |
Other editions - View all
Making a Machine That Sees Like Us Zygmunt Pizlo,Yunfeng Li,Tadamasa Sawada,Robert M. Steinman Limited preview - 2014 |
Common terms and phrases
2D image 2D retinal image 3D object 3D scene 3D shape 3D symmetrical able actually allows applied assume axis binocular called chair claim compactness completely computational contours correspondence curves degenerate demo depth described developed difficult direction dots effective environment example experiment explain face fact Figure flat geometrical geometry going human important interpretation Inverse Problems kind least look machine means measured mirror-symmetrical namely natural needed never Note observer Once operation orientation orthographic pairs parallel perceived perfect performance perspective physical Pizlo planar plane points position possible present priori constraints probably problem produced projection recovered recovery represent representation role sense shape constancy shape perception shown shows similar simply single solution solve space stimulus surface symmetry Technically theory tion veridical vertical viewing vision visual perception visual system