Motion is a crucial cue for human object perception. Previous studies have demonstrated that humans can recognize objects even in synthetic random dot stimuli where only motion, not appearance, is informative. Remarkably, this works without prior exposure to these types of stimuli, indicating a purely zero-shot capability akin to Wertheimer’s “common fate” {\it Gestalt} principle, proposed a hundred years ago as a “law of organization in perceptual forms.”Here, we evaluate computer vision approaches and a neuroscience inspired motion energy model for zero-shot figure-ground segmentation of random dot stimuli.Examining a broad range of models, we find that state-of-the-art optical flow models struggle to estimate motion patterns in random dot videos, resulting in poor figure-ground segmentation performance. Conversely, the neuroscience-inspired model significantly outperforms all optical flow models in this context.For a direct comparison, we conduct a psychophysical study using a shape identification task as a proxy to measure human segmentation performance.All state-of-the-art optical flow models fall short of human performance, but only the motion energy model matches human capability. Specifically, we use the extensively validated motion energy model proposed by Simoncelli and Heeger in 1998 which is fitted to a broad range of neural recordings in cortex area MT. This neuroscience-inspired model successfully addresses the lack of human-like zero-shot generalization to random dot stimuli in current computer vision models, and thus establishes a compelling link between the Gestalt psychology of human object perception and cortical motion processing in the brain. Code, models and datasets will be published.