Overall, the project has successfully achieved its goals and in several aspects has even exceeded them. In particular, the project has led to 64 scientific publications in top venues including NeurIPS, SIGGRAPH, CVPR, ICCV, ICML, SIGGRAPH Asia and others. These papers have received 7 best paper awards or nominations. The majority of these publications are of core relevance to the project, and have helped to lay the foundations, both theoretical and computational for analysing, processing and even synthesizing geometric data using the general methodology outlined in the project proposal, which is based on the functional maps framework.
Within this project we have built upon a novel paradigm in geometric data analysis, which considers objects as functional spaces rather than collections of points or triangles. This point of view has proved extremely productive and has enabled efficient algorithms that can process, manipulate, analyze and compare 3D shapes, while treating them as functional spaces.
This project has led to several breakthrough results, and has significantly pushed the state-of-the-art in terms of accuracy and robustness of the best available techniques for shape comparison. A major contribution of this project is a set of novel theoretical insights and practical methods for 3D shape analysis based on the functional maps framework. The new results obtained within this project have significantly improved the robustness, accuracy and speed of the best available methods for computing correspondences and quantifying similarity across different 3D shapes. This includes both axiomatic as well as learning-based approaches.
In addition to its foundational nature, the project has also led to several practical applications in diverse scientific and industrial settings. This includes collaborations by the PI with the Necker Children's Hospital, The Museum of Mankind, as well as in bio-medical context such as for analysis of protein or evolving biological cell data. In all of these disciplines, the key problem is to reliably establish correspondences and quantify similarity and differences across diverse shapes. The methods that we have developed within this project have thus allowed researchers and practitioners in these domains to significantly improve the accuracy of their shape analysis pipelines.
Our work has been recognized through extensive publication record in peer-reviewed journals and conference proceedings. Furthermore, several papers have been selected for prestigious awards. Finally, the members of the project, including the PI Maks Ovsjanikov have been active in the computer vision, computer graphics and geometry processing communities to disseminate their works and as active community service members.
