Superresolution (SR) has provided an effective solution to the increasing need for high-resolution images in remote sensing applications. Among various SR methods, deep learningbased SR (DLSR) has made a significant breakthrough. However, supervised DLSR methods require a considerable amount of training data, which is hardly available in the remote sensing field. To address this issue, some research works have recently proposed and revealed the capability of deep learning in unsupervised SR. This article presents an efficient unsupervised SR (EUSR) deep learning model using dense skip connections, which boosts the reconstruction performance in parallel with the reduction of computational burden. To do this, several blocks containing densely connected convolutional layers are implemented to increase the depth of the model. Some skip connections also concatenate feature maps of different blocks to enable better SR performance. Moreover, a bottle-neck block abstracts the feature maps in fewer feature maps to remarkably reduce the computational burden. According to our experiments, the proposed EUSR leads to better results than the state-of-the-art DLSR method in terms of reconstruction quality with less computational burden. Furthermore, results indicate that the EUSR is more robust than its rival in dealing with images of different classes and larger sizes.

Abstract. Thanks to the proliferation of commodity 3D devices such as HoloLens, one can have easy access to the 3D model of indoor building objects. However, this model does not match 2D available computer-aided design (CAD) models as the as-built model. To address this problem, in this study, a 3-step registration method is proposed. First, binary images, including walls and background, are generated for the 3D point cloud (PC) and the 2D CAD model. Then, 2D-to-2D corresponding pixels (CPs) are extracted based on the intersection of walls in each binary image of PC (BIPC) and binary CAD (BCAD) model. Since the 3D PC space coordinates (XYZ) of all BIPC's pixels are known, BIPC part of the 2D-to-2D CPs can be considered 3D. Lastly, the parameters of the 8-parameter affine are estimated using the 2D-to-3D CPs, which are pixel coordinates in BCAD model as well as their correspondences in the 3D PC space. Experimental results indicate the efficiency of our proposed method compared to manual registration.

Rational function model (<small>RFM</small>) is the most widely used sensor model in the remote sensing community. However, it suffers from ill-posedness, challenging its feasibility. This problem, i.e., ill-posedness, is mainly caused due to highly correlated coefficients of the <small>RFM</small>, which magnifies any small perturbations of observations, such as noise and instrumental error. This paper outlines a novel two-step method, called principal component analysis (<small>PCA</small>)-<small>RFM</small>, based on the integration of <small>PCA</small> and QR decomposition. In the first step, the <small>PCA</small>-<small>RFM</small> reduces the observational perturbations from the design matrix using the <small>PCA</small>. In the next step, the <small>RFM</small>'s coefficients are estimated using a <small>QR</small> decomposition with column pivoting and least square method. According to the results, the <small>PCA</small>-<small>RFM</small> is less sensitive than its rivals to the changes of the ground control point (<small>GCPs</small>) distribution. Geometrically speaking, in addition, <small>PCA</small>-<small>RFM</small> is more accurate than recently established methods even in the presence of the small number of <small>GCPs</small>.

No abstract

Deep learning, specifically the supervised approach, has proved to be a breakthrough in depth prediction. However, the generalization ability of deep networks is still limited, and they cannot maintain a satisfactory performance on some inputs. Addressing a similar problem in the segmentation field, a scheme (f-BRS) has been proposed to refine predictions in the inference time. f-BRS adapts an intermediate activation function to each input by using user clicks as sparse labels. Given the similarity between user clicks and sparse depth maps, this paper aims at extending the application of f-BRS to depth prediction. Our experiments show that f-BRS, fused with a depth estimation baseline, is trapped in local optima, and fails to improve the network predictions. To resolve that, we propose a double-stage adaptive refinement scheme (DARS). In the first stage, a Delaunay-based correction module significantly improves the depth generated by a baseline network. In the second stage, a particle swarm optimizer (PSO) delineates the estimation through fine-tuning f-BRS parameters&mdash;that is, scales and biases. DARS is evaluated on an outdoor benchmark, KITTI, and an indoor benchmark, NYUv2 while for both the network is pre-trained on KITTI. The proposed scheme outperformed rival methods on both datasets.