Where to draw the line?

We often take people’s ability to understand and produce line drawings for granted. But where should we draw lines, and why? We address psychological principles that underlie efficient representations of complex information in line drawings. First, 58 participants with varying degree of artistic experience produced multiple drawings of a small set of scenes by tracing contours on a digital tablet. Second, 37 independent observers ranked the drawings by how representative they are of the original photograph. Matching contours between drawings of the same scene revealed that the most consistently drawn contours tend to be drawn earlier. We generated half-images with the most- versus least-consistently drawn contours and asked 25 observers categorize the quickly presented scenes. Observers performed significantly better for the most compared to the least consistent half-images. The most consistently drawn contours were more likely to depict occlusion boundaries, whereas the least consistently drawn contours frequently depicted surface normals.

Where to Draw The Line?

We often take people’s ability to understand and produce line drawings for granted. But where should we draw lines, and why? We address fundamental principles that underlie efficient representations of complex information in line drawings. First, 58 participants with varying degree of artistic experience produced multiple drawings of a small set of scenes by tracing contours on a digital tablet. Second, 37 independent observers ranked the drawings by how representative they are of the original photograph. Overall, artists’ drawings ranked higher than non-artists’. Matching contours between drawings of the same scene revealed that the most consistently drawn contours tend to be drawn earlier. We generated half-images with the most-versus least-consistently drawn contours by sorting contours by their consistency scores. Twenty five observers performed significantly better in a fast scene categorization task for the most compared to the least consistent half-images. The most consistent contours were longer and more likely to depict occlusion boundaries. Using psychophysics experiments and computational analysis, we confirmed quantitatively what makes certain contours in line drawings special: longer contours mark occlusion boundaries and aid rapid scene recognition. They allow artist and non-artists to convey important information starting from the first few strokes in their drawing process.

Learning attention-controllable border-ownership for objectness inference and binding

Human visual systems can parse a scene composed of novel objects and infer their surfaces and occlusion relationships without relying on object-specific shapes or textures. Perceptual grouping can bind together spatially disjoint entities to unite them as one object even when the object is entirely novel, and bind other perceptual properties like color and texture to that object using object-based attention. Border-ownership assignment, the assignment of perceived occlusion boundaries to specific perceived surfaces, is an intermediate representation in the mammalian visual system that facilitates this perceptual grouping. Since objects in a scene can be entirely novel, inferring border ownership requires integrating global figural information, while dynamically postulating what the figure is, a chicken-and egg process that is complicated further by missing or conflicting local evidence regarding the presence of boundaries. Based on neuroscience observations, we introduce a model -- the cloned Markov random field (CMRF)-- that can learn attention-controllable representations for border-ownership. Higher-order contour representations that distinguish border-ownerships emerge as part of learning in this model. When tested with a cluttered scene of novel 2D objects with noisy contour-only evidence, the CMRF model is able to perceptually group them, despite clutter and missing edges. Moreover, the CMRF is able to use occlusion cues to bind disconnected surface elements of novel objects into coherent objects, and able to use top-down attention to assign border ownership to overlapping objects. Our work is a step towards dynamic binding of surface elements into objects, a capability that is crucial for intelligent agents to interact with the world and to form entity-based abstractions.

3D reconstruction by a combined structure tensor and Hough transform light field approach

Disparity estimation using the structure tensor is a local approach to determine orientation in Epipolar Plane Images. A global extension would lead to more precise and robust estimations. In this work, a novel algorithm for 3D reconstruction from linear light fields is proposed. This method uses a modified version of the Progressive Probabilistic Hough Transform to extract orientations from Epipolar Plane Images, allowing to achieve high quality disparity maps. To this aim, the structure tensor estimates are used to speed up computation and improve the disparity estimation near occlusion boundaries. The new algorithm is evaluated on both synthetic and real light field datasets, and compared with classical local disparity estimation techniques based on the structure tensor.