Search

Decoupling shading and reflectance from complex scene-images is a long-standing problem in computer vision. We introduce a framework for decomposing an image into the product of an illumination component and a reflectance component. Due to the ill-posed nature of the problem, prior information on shading and reflectance is mandatory. The proposed method adopts the premise that pixels in a region with similar chromaticity values should have the same reflectance. This assumption was used to minimize the l2 norm of the local per-pixel reflectance gradients to extract the shading and reflectance components. To obtain smooth chromatic regions, texture was treated in a new style. Texture was removed in the first step of the algorithm and the smooth image was processed for intrinsic decomposition. In the final step, texture details were added to the intrinsic components based on the material of each pixel. In addition, user-assistance was used to further refine the results. The qualitative and quantitative evaluation on the MIT intrinsic dataset indicated that the quality of intrinsic image decomposition was improved in comparison with previous methods.

Traffic pattern is a point of concern in today's modeling approach of network-based computing systems including NoC's and Clusters. Hypermesh is a promising network topology suitable for a range of networks. Although there are few models reported for hypermeshes with uniform traffic pattern, no analytical model has been reported yet that deal with hotspot traffic load. Since uniform traffic assumption is not always justifiable in practice as there are many parallel applications that exhibit non-uniform traffic patterns, which can produce hotspots in the network, in this study we propose a novel analytical model to analyze the mean message latency in wormhole-switched hypermesh in the presence of hot-spot traffic.