Inpainting-based image compression is an emerging paradigm for compressing visual data in a completely different way than popular transform-based methods such as JPEG. The underlying idea sounds very simple: One stores only a small, carefully selected subset of the data, which results in a substantial reduction of the file size. In the decoding phase, one interpolates the missing data by means ...

Recent advances in deep generative models have shown promising potential in image inpanting, which refers to the task of predicting missing pixel values of an incomplete image using the known context. However, existing methods can be slow or generate unsatisfying results with easily detectable flaws. In addition, there is often perceivable discontinuity near the holes and require further post-p...

This work presents a procedure for refining depth maps acquired using RGB-D (depth) cameras. With numerous new structured-light RGB-D cameras, acquiring high-resolution depth maps has become easy. However, there are problems such as undesired occlusion, inaccurate depth values, and temporal variation of pixel values when using these cameras. In this paper, a proposed method based on an exemplar...

Some recent methods for lossy signal and image compression store only a few selected pixels and fill in the missing structures by inpainting with a partial differential equation (PDE). Suitable operators include the Laplacian, the biharmonic operator, and edge-enhancing anisotropic diffusion (EED). The quality of such approaches depends substantially on the selection of the data that is kept. O...

As a specific application of image inpainting, face inpainting is critical content in the computer vision. It plays an important role object removal, photo editing and other fields. Deep learning has become mainstream approach inpainting. In applications, corrupted area images usually irregular. For classical irregular approaches based on deep learning, this paper divides it into convolution op...

We describe an autonomous production system that utilizes Computational Fluid Dynamics (CFD) techniques and Partial Differential Equations (PDEs) to create accurate textured 3D site models with LiDAR, IFSAR, and stereo imagery. LiDAR is the data set of choice for specific urban scenes. IFSAR or stereo imagery is used for broad areas to mitigate cost. A high resolution Digital Surface Model (DSM...

Recovering lost part of an image plays a great role in image processing. Inpainting is a technique that helps in recovering lost pixels from an image. From the existing techniques of Inpainting, Exemplar Inpainting is one of the fast and better techniques that help in restoring the lost part of an image. Exemplar based method chooses a patch similar to the lost patch from the known area to fill...

Recovering lost part of an image plays a great role in image processing. Inpainting is a technique that helps in recovering lost pixels from an image. From the existing techniques of Inpainting, Exemplar Inpainting is one of the fast and better techniques that help in restoring the lost part of an image. Exemplar based method chooses a patch similar to the lost patch from the known area to fill...

We present a novel approach to low-level vision problems that combines sparse coding and deep networks pre-trained with denoising auto-encoder (DA). We propose an alternative training scheme that successfully adapts DA, originally designed for unsupervised feature learning, to the tasks of image denoising and blind inpainting. Our method’s performance in the image denoising task is comparable t...

Recovering lost part of an image plays a great role in image processing. Inpainting is a technique that helps in recovering lost pixels from an image. From the existing techniques of Inpainting, Exemplar Inpainting is one of the fast and better techniques that help in restoring the lost part of an image. Exemplar based method chooses a patch similar to the lost patch from the known area to fill...