Progetto Recover

Being appealing to a wide audience, the cultural sector can supply several compelling forms of digital content suited for a diverse spectrum of uses, ranging from learning and entertainment to study of art history and cultural documentation. For this reason, the development of culture-related IT products and services has been the focus of a large number of efforts worldwide, originating both from companies and Government agencies. This is particularly true in Europe because of its long cultural heritage and immense repository of artistic treasures.

RECOVER (full title “Photorealistic 3D Reconstruction of Perspective Paintings and Pictures”) is an EU co-operative research project that aims to develop a system for the semi-automatic extraction of three-dimensional (3D) models of scenes depicted in perspective paintings, gravures, postcards and old photographs. 3D models of paintings constitute a new and exciting way for the general public to experience and appreciate fine art. Their viewer can experience a feeling of immersion; paintings are no longer perceived as static artifacts from a long-gone past but as living, vibrant entities. With the aid of appropriate software, the viewer can literally dive into the painting, interacting with it and observing it from various viewpoints in impressive walk-throughs and inspiring fly-bys. This enables non-specialists to step into history and experience the scene in the space and time frame perceived by the artist. Ultimately, the viewing of paintings becomes a more appealing, exploratory endeavor, arousing the public’s interest in fine art and cultural heritage in general.


According to the current state-of-practice, fully manual techniques based on the use of CAD and 3D modeling tools for reconstructing paintings are quite tedious and labor-intensive, therefore time-consuming and expensive. Conventional 3D laser scanning techniques are inapplicable due to the fact that the canvas used for painting is 2D. RECOVER, on the other hand, capitalizes on a vast body of research knowledge in order to bridge the gap between the research state-of-the-art and the state-of-practice in the construction of 3D models from 2D paintings. To achieve this, it employs non-contact computer vision techniques to infer 3D scene structure by “inverting” perspective image formation which lays down the geometric rules followed by painters when drawing. The focus is on the reconstruction of paintings that are rich in planes, colinearities, symmetries, orthogonalities and other forms of geometric regularity. Furthermore, the resulting 3D information is refined and enhanced with the aid of interactive editing tools, yielding a photorealistic 3D model of the depicted scene.


The primary envisaged use for the 3D models obtained with RECOVER is to employ them as the digital content for real-time virtual reality applications which improve the accessibility and visibility of cultural resources. Apart from this, however, RECOVER technology can have a broad spectrum of possible practical applications ranging from the study of art history and assistive technologies for people with special needs to video metrology, architectural photogrammetry and surveying engineering, urban visualization and planning, monuments preservation and conservation, forensic science, maintenance, guidance and information and e-learning.