Biologically plausible neural models can account for binocular disparity
the verdict
SUPPORTED
the evidence backs this
confidence 81/100
Multiple computational and neuroscience studies demonstrate that biologically plausible neural network models can effectively account for binocular disparity and depth perception.
Evidence for · 4
Active Vision in Binocular Depth Estimation: A Top-Down Perspective.
2023 · cited by 7
The paper demonstrates that depth estimation from binocular disparity can be implemented via biologically plausible hierarchical generative models and predictive coding.
See more details
More for · 3
Understanding and simulating border ownership centered segmentation.
2025 · cited by 0
The study integrates binocular disparity representation within a comprehensive neural model of border ownership and figure-ground organization.
Human and artificial visual systems share a computational principle for transforming binocular disparity into depth representation.
2025 · cited by 0
Research shows that both human visual cortices and artificial deep neural networks share computational principles for transforming binocular disparity into depth representations.
Learning bio-inspired head-centric representations of 3D shapes in an active fixation setting.
2022 · cited by 0
A recurrent neural network modeling population responses of cortical V1 cells successfully interprets 3D scene depth from binocular disparity.