Kernkonzepte
Unsupervised framework harmonizing spectral and spatial maps for accurate 3D shape matching and realistic interpolation.
Statistiken
"Our method outperforms the previous state-of-the-art methods."
"Our method achieves substan- tially better cross-dataset generalisation ability than existing learning-based methods."
Zitate
"Our method sets the new state of the art in both shape matching and interpolation on numerous benchmarks."
"Our method achieves state-of-the-art performance on both datasets, even compared to methods relying on ground-truth correspondences."