This paper introduces a novel algorithm for automatic digital inpainting that aims to replicate the basic techniques used by professional restorators. The algorithm allows users to select regions to be restored, and then automatically fills these regions with information from their surroundings. The fill-in process ensures that isophote lines arriving at the boundaries of the regions are completed inside. Unlike previous methods, this algorithm does not require the user to specify where the new information comes from, allowing it to simultaneously fill in multiple regions with different structures and backgrounds. The algorithm is not limited by the topology of the region to be inpainted and can be used for various applications such as restoring old photographs and damaged film, removing superimposed text, and removing entire objects from images. The algorithm is based on the idea of smoothly propagating information from surrounding areas in the isophote direction. It uses anisotropic diffusion to achieve this, which helps in preserving sharpness in the reconstructed image. The algorithm is implemented in a way that allows for the propagation of both gray-value and isophote direction information, which is essential for the success of the algorithm. The algorithm is also capable of handling large regions and is not limited by the size or complexity of the region to be inpainted. The algorithm has been tested on various examples, including synthetic images, deteriorated black and white images, and color images with superimposed text. The results show that the algorithm can effectively restore images with a wide range of applications, including the restoration of old photographs and damaged film, removal of superimposed text, and removal of objects. The algorithm is efficient and can be used to provide an initial point for manual restoration, thereby reducing the total restoration time by orders of magnitude. The algorithm is motivated by and has borrowed from the intensive work on the use of Partial Differential Equations (PDEs) in image processing and computer vision. The algorithm has been tested in conjunction with texture synthesis ideas to address the issue of reproducing large textured regions. The algorithm is currently being tested for its ability to automatically switch between textured and geometric areas, and select the best suited technique for each region. The algorithm is also being investigated for its ability to inpaint from partial degradation, which is an important aspect of image restoration. The algorithm has been supported by various grants and funding from different organizations, including the Office of Naval Research, the National Science Foundation, and the Universidad de la República.This paper introduces a novel algorithm for automatic digital inpainting that aims to replicate the basic techniques used by professional restorators. The algorithm allows users to select regions to be restored, and then automatically fills these regions with information from their surroundings. The fill-in process ensures that isophote lines arriving at the boundaries of the regions are completed inside. Unlike previous methods, this algorithm does not require the user to specify where the new information comes from, allowing it to simultaneously fill in multiple regions with different structures and backgrounds. The algorithm is not limited by the topology of the region to be inpainted and can be used for various applications such as restoring old photographs and damaged film, removing superimposed text, and removing entire objects from images. The algorithm is based on the idea of smoothly propagating information from surrounding areas in the isophote direction. It uses anisotropic diffusion to achieve this, which helps in preserving sharpness in the reconstructed image. The algorithm is implemented in a way that allows for the propagation of both gray-value and isophote direction information, which is essential for the success of the algorithm. The algorithm is also capable of handling large regions and is not limited by the size or complexity of the region to be inpainted. The algorithm has been tested on various examples, including synthetic images, deteriorated black and white images, and color images with superimposed text. The results show that the algorithm can effectively restore images with a wide range of applications, including the restoration of old photographs and damaged film, removal of superimposed text, and removal of objects. The algorithm is efficient and can be used to provide an initial point for manual restoration, thereby reducing the total restoration time by orders of magnitude. The algorithm is motivated by and has borrowed from the intensive work on the use of Partial Differential Equations (PDEs) in image processing and computer vision. The algorithm has been tested in conjunction with texture synthesis ideas to address the issue of reproducing large textured regions. The algorithm is currently being tested for its ability to automatically switch between textured and geometric areas, and select the best suited technique for each region. The algorithm is also being investigated for its ability to inpaint from partial degradation, which is an important aspect of image restoration. The algorithm has been supported by various grants and funding from different organizations, including the Office of Naval Research, the National Science Foundation, and the Universidad de la República.