Both humans and deep learning models can recognize objects from 3D shapes depicted with sparse visual information, such as a set of points randomly sampled from the surfaces of 3D objects (termed a point cloud). Although deep learning models achieve human-like performance in recognizing objects from 3D shapes, it remains unclear whether these models develop 3D shape representations similar to those used by human vision for object recognition. Evidence suggests that training with approximately 10,000 object instances enables models to acquire representations of local geometric structures in 3D shapes. We hypothesize, however, that their representations of 3D global shapes are still limited. To test this hypothesis, we conducted three human experiments systematically manipulating point density and object orientation (Experiment 1), local geometric structure (Experiment 2), and part configuration (Experiment 3). Human performance was stable across conditions in the first two experiments, but declined significantly in the part-scrambled condition of the final experiment. We compared human performance with two types of deep learning architectures: convolution-based models (e.g., DGCNN) and transformer-based models (e.g., Point Transformer). The transformer-based models more closely captured human performance patterns across experimental conditions. Ablation simulations revealed that this advantage is largely driven by progressive downsampling operations that enable hierarchical abstraction of 3D shapes.

Deep convolutional networks (DCNNs) are achieving previously unseen performance in object classification, raising questions about whether DCNNs operate similarly to human vision.In biological vision, shape is arguably the most important cue for recognition.We tested the role of shape information in DCNNs trained to recognize objects.In Experiment 1, we presented a trained DCNN with object silhouettes that preserved overall shape but were filled with surface texture taken from other objects.Shape cues appeared to play some role in the classification of artifacts, but little or none for animals.In Experiments 2-4, DCNNs showed no ability to classify glass figurines or outlines but correctly classified some silhouettes.Aspects of these results led us to hypothesize that DCNNs do not distinguish object's bounding contours from other edges, and that DCNNs access some local shape features, but not global shape.In Experiment 5, we tested this hypothesis with displays that preserved local features but disrupted global shape, and vice versa.With disrupted global shape, which reduced human accuracy to 28%, DCNNs gave the same classification labels as with ordinary shapes.Conversely, local contour changes eliminated accurate DCNN classification but caused no difficulty for human observers.These results provide evidence that DCNNs have access to some local shape information in the form of local edge relations, but they have no access to global object shapes. Author summary"Deep learning" systems-specifically, deep convolutional neural networks (DCNNs)have recently achieved near human levels of performance in object recognition tasks.It has been suggested that the processing in these systems may model or explain object perception abilities in biological vision.For humans, shape is the most important cue for recognizing objects.We tested whether deep convolutional neural networks trained to recognize objects make use of object shape.Our findings indicate that other cues, such as surface texture, play a larger role in deep network classification than in human recognition.Most crucially, we show that deep learning systems have no sensitivity to the overall shape of an object.Whereas deep learning systems can access some local shape features,

We examined graphical representations of aircraft altitude in simulated air traffic control (ATC) displays. In two experiments, size and contrast cues correlated with altitude improved participants' ability to detect future aircraft collisions (conflicts). Experiment 1 demonstrated that, across several set sizes, contrast and size cues to altitude improved accuracy at identifying conflicts. Experiment 2 demonstrated that graphical cues for representing altitude both improved accuracy and reduced search time for finding conflicts in large set size displays. The addition of size and contrast cues to ATC displays may offer specific benefits in aircraft conflict detection.

Perception of object depends on a number of interacting information processing tasks. This paper gives a brief overview of processes of contour and object perceptions that overcome fragmentary input and produce representation of objects. A simple geometry accounting for contour interpolation is described, and its application to 2-D, 3-D, and spatiotemporal object interpolation processes is considered. Some aspects of the model -- especially the unified treatment of illusory and occluded objects -- raise questions about the nature of seeing. Although it is often believed that illusory objects are perceived, while occluded objects are inferred, I suggest that both the representational theory of mind and the result of research converge in supporting the unified account. Illusory and occluded contours and surfaces do not divide into the real, the perceived, and the inferred, but are all represented, and in key, derive from identical perceptual processes.