Search for: All records

Image segmentation is a fundamental task that has benefited from recent advances in machine learning. One type of segmentation, of particular interest to computer vision, is that of urban segmentation. Although recent solutions have leveraged on deep neural networks, approaches usually do not consider regularities appearing in facade structures (e.g., windows are often in groups of similar alignment, size, or spacing patterns) as well as additional urban structures such as building footprints and roofs. Moreover, both satellite and street-view images are often noisy and occluded, thus getting the complete structure segmentation from a partial observation is difficult. Our key observations are that facades and other urban structures exhibit regular structures, and additional views are often available. In this paper, we present a novel framework (RFCNet) that consists of three modules to achieve multiple goals. Specifically, we propose Regularization to improve the regularities given an initial segmentation, Fusion that fuses multiple views of the segmentation, and Completion that can infer the complete structure if necessary. Experimental results show that our method outperforms previous state-of-the-art methods quantitatively and qualitatively for multiple facade datasets. Furthermore, by applying our framework to other urban structures (e.g., building footprints and roofs), we demonstrate our approach can be generalized to various pattern types. 

Image/sketch completion is a core task that addresses the problem of completing the missing regions of an image/sketch with realistic and semantically consistent content. We address one type of completion which is producing a tentative completion of an aerial view of the remnants of a building structure. The inference process may start with as little as 10% of the structure and thus is fundamentally pluralistic (e.g., multiple completions are possible). We present a novel pluralistic building contour completion framework. A feature suggestion component uses an entropy-based model to request information from the user for the next most informative location in the image. Then, an image completion component trained using self-supervision and procedurally-generated content produces a partial or full completion. In our synthetic and real-world experiments for archaeological sites in Turkey, with up to only 4 iterations, we complete building footprints having only 10-15% of the ancient structure initially visible. We also compare to various state-of-the-art methods and show our superior quantitative/qualitative performance. While we show results for archaeology, we anticipate our method can be used for restoring highly incomplete historical sketches and for modern day urban reconstruction despite occlusions. 

Abstract Flowering plants have evolved numerous intraspecific and interspecific prezygotic reproductive barriers to prevent production of unfavourable offspring 1 . Within a species, self-incompatibility (SI) is a widely utilized mechanism that rejects self-pollen 2,3 to avoid inbreeding depression. Interspecific barriers restrain breeding between species and often follow the SI × self-compatible (SC) rule, that is, interspecific pollen is unilaterally incompatible (UI) on SI pistils but unilaterally compatible (UC) on SC pistils 1,4–6 . The molecular mechanisms underlying SI, UI, SC and UC and their interconnections in the Brassicaceae remain unclear. Here we demonstrate that the SI pollen determinant S -locus cysteine-rich protein/ S -locus protein 11 (SCR/SP11) 2,3 or a signal from UI pollen binds to the SI female determinant S -locus receptor kinase (SRK) 2,3 , recruits FERONIA (FER) 7–9 and activates FER-mediated reactive oxygen species production in SI stigmas 10,11 to reject incompatible pollen. For compatible responses, diverged pollen coat protein B-class 12–14 from SC and UC pollen differentially trigger nitric oxide, nitrosate FER to suppress reactive oxygen species in SC stigmas to facilitate pollen growth in an intraspecies-preferential manner, maintaining species integrity. Our results show that SRK and FER integrate mechanisms underlying intraspecific and interspecific barriers and offer paths to achieve distant breeding in Brassicaceae crops.