Generalized Boundaries from Multiple Image Interpretations
This work addresses the need for efficient and versatile boundary detection in computer vision tasks like segmentation and recognition, offering a practical solution with broad applicability.
The paper tackles the problem of detecting various types of boundaries in computer vision, such as intensity edges and occlusion boundaries, by proposing a unified formulation and algorithm that achieves state-of-the-art performance with significantly lower computational cost.
Boundary detection is essential for a variety of computer vision tasks such as segmentation and recognition. In this paper we propose a unified formulation and a novel algorithm that are applicable to the detection of different types of boundaries, such as intensity edges, occlusion boundaries or object category specific boundaries. Our formulation leads to a simple method with state-of-the-art performance and significantly lower computational cost than existing methods. We evaluate our algorithm on different types of boundaries, from low-level boundaries extracted in natural images, to occlusion boundaries obtained using motion cues and RGB-D cameras, to boundaries from soft-segmentation. We also propose a novel method for figure/ground soft-segmentation that can be used in conjunction with our boundary detection method and improve its accuracy at almost no extra computational cost.