no code implementations • 21 Dec 2024 • Souhaib Attaiki, Paul Guerrero, Duygu Ceylan, Niloy J. Mitra, Maks Ovsjanikov
We observe that GAN- and diffusion-based generators have complementary qualities: GANs can be trained efficiently with 2D supervision to produce high-quality 3D objects but are hard to condition on text.
1 code implementation • NeurIPS 2023 • Souhaib Attaiki, Maks Ovsjanikov
We present Shape Non-rigid Kinematics (SNK), a novel zero-shot method for non-rigid shape matching that eliminates the need for extensive training or ground truth data.
no code implementations • 27 Oct 2023 • Sara Hahner, Souhaib Attaiki, Jochen Garcke, Maks Ovsjanikov
Unlike previous 3D mesh autoencoders that require meshes to be in a 1-to-1 correspondence, our approach is trained on diverse meshes in an unsupervised manner.
2 code implementations • 28 Sep 2023 • Vincent Mallet, Souhaib Attaiki, Yangyang Miao, Bruno Correia, Maks Ovsjanikov
In particular, there is a lack of direct and fair benchmark comparison between the best available surface-based learning methods against alternative representations such as graphs.
no code implementations • CVPR 2023 • Souhaib Attaiki, Maks Ovsjanikov
In this paper, we show that under some mild conditions, the features learned within deep functional map approaches can be used as point-wise descriptors and thus are directly comparable across different shapes, even without the necessity of solving for a functional map at test time.
1 code implementation • CVPR 2023 • Souhaib Attaiki, Lei LI, Maks Ovsjanikov
We observe that with proper training, learned features can be useful in such tasks, but, crucially, only with an appropriate choice of the receptive field size.
1 code implementation • 14 Jan 2023 • Souhaib Attaiki, Maks Ovsjanikov
We present Neural Correspondence Prior (NCP), a new paradigm for computing correspondences between 3D shapes.
1 code implementation • 16 Sep 2022 • Lei LI, Souhaib Attaiki, Maks Ovsjanikov
In this work, we present a novel learning-based framework that combines the local accuracy of contrastive learning with the global consistency of geometric approaches, for robust non-rigid matching.
1 code implementation • 14 Dec 2021 • Riccardo Marin, Souhaib Attaiki, Simone Melzi, Emanuele Rodolà, Maks Ovsjanikov
In this study, we analyze, for the first time, properties that arise in data-driven learned embedding and their relation to the shape-matching task.
1 code implementation • 19 Oct 2021 • Souhaib Attaiki, Gautam Pai, Maks Ovsjanikov
We consider the problem of computing dense correspondences between non-rigid shapes with potentially significant partiality.
4 code implementations • 1 Dec 2020 • Nicholas Sharp, Souhaib Attaiki, Keenan Crane, Maks Ovsjanikov
We introduce a new general-purpose approach to deep learning on 3D surfaces, based on the insight that a simple diffusion layer is highly effective for spatial communication.