A robust receptive field code for optic flow detection and decomposition during self-motion

The perception of optic flow is essential for any visually guided behaviour of a moving animal. To mechanistically predict behaviour and understand the emergence of self-motion perception in vertebrate brains, it is essential to systematically characterize the motion receptive fields (RFs) of optic flow processing neurons. Here, we present the fine-scale RFs of thousands of motion-sensitive neurons studied in the diencephalon and the midbrain of zebrafish. We found neurons that serve as linear filters and robustly encode directional and speed information of translation-induced optic flow. These neurons are topographically arranged in pretectum according to translation direction. The unambiguous encoding of translation enables the decomposition of translational and rotational self-motion information from mixed optic flow. In behavioural experiments, we successfully demonstrated the predicted decomposition in the optokinetic and optomotor responses. Together, our study reveals the algorithm and the neural implementation for self-motion estimation in a vertebrate visual system.