Depth Super-Resolution via Joint Color-Guided Internal and External Regularizations


Many real-world applications make heavy use of depth information. In practise, however, depth maps tend to have a lower resolution than colour images because of the limitations of depth sensor technologies. To achieve depth super-resolution, we propose to combine the internal smoothness prior and the exterior gradient consistency requirement in graph domain. Firstly, a novel graph Laplacian regularizer is presented to preserve the depth's inherent piecewise smoothness, which has useful filtering qualities. The weight matrix of the respect graph has been defined to take advantage of both depth and the related guidance image. In contrast, we introduce a graph gradient consistency constraint to guarantee that the graph gradient of depth is near to the thresholded gradient of guidance, inspired by the finding that the gradient of depth is modest except at edge separation regions. The gradient thresholding model is reinterpreted as variational optimization with a sparsity constraint. Here, we address the issue of structure inconsistency between the depth and guidance. Finally, a unified optimization framework incorporating both internal and external regularizations may be addressed effectively by ADMM. Experiments show that our strategy outperforms the current state of the art in terms of both objective and subjective quality evaluations.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : CANet Cross-Disease Attention Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Grading ABSTRACT: One in three people who are working-age and have diabetes will go blind due to diabetic retinopathy
PROJECT TITLE : Depth Restoration From RGB-D Data via Joint Adaptive Regularization and Thresholding on Manifolds ABSTRACT: By integrating the properties of local and non-local manifolds that offer low-dimensional parameterizations
PROJECT TITLE : Graph-based Joint Dequantization and Contrast Enhancement of Poorly Lit JPEG Images ABSTRACT: The lossy compression of JPEG images results in images with low contrast and coarse quantization artefacts in low-light
PROJECT TITLE : Graph-Regularized Locality-Constrained Joint Dictionary and Residual Learning for Face Sketch Synthesis ABSTRACT: For digital entertainment and police enforcement, face sketch synthesis is a critical issue It's
PROJECT TITLE : Image Co-Saliency Detection and Co-Segmentation via Progressive Joint Optimization ABSTRACT: New computational models for simultaneous picture co-saliency detection and co-segmentation are presented here that simultaneously

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry