no code implementations • 26 Feb 2024 • Dmitry Petrov, Pradyumn Goyal, Vikas Thamizharasan, Vladimir G. Kim, Matheus Gadelha, Melinos Averkiou, Siddhartha Chaudhuri, Evangelos Kalogerakis
We introduce GEM3D -- a new deep, topology-aware generative model of 3D shapes.
no code implementations • 27 May 2022 • Dmitry Petrov, Matheus Gadelha, Radomir Mech, Evangelos Kalogerakis
Reconstructions can be obtained in two ways: (i) by directly decoding the part latent codes to part implicit functions, then combining them into the final shape; or (ii) by using part latents to retrieve similar part instances in a part database and assembling them in a single shape.
1 code implementation • 20 Mar 2020 • Marios Loizou, Siddhant Garg, Dmitry Petrov, Melinos Averkiou, Evangelos Kalogerakis
The mechanism assesses both the degree of interaction between points and also mediates feature propagation across shapes, improving the accuracy and consistency of the resulting point-wise feature representations for shape segmentation.
Ranked #1 on 3D Semantic Segmentation on PartNet
1 code implementation • 19 Jun 2017 • Dmitry Petrov, Alexander Ivanov, Joshua Faskowitz, Boris Gutman, Daniel Moyer, Julio Villalon, Neda Jahanshad, Paul Thompson
There is no consensus on how to construct structural brain networks from diffusion MRI.
no code implementations • 26 Jan 2017 • Dmitry Petrov, Boris Gutman, Alexander Ivanov, Joshua Faskowitz, Neda Jahanshad, Mikhail Belyaev, Paul Thompson
In this work, we study the extent to which structural connectomes and topological derivative measures are unique to individual changes within human brains.
no code implementations • 27 Nov 2016 • Yulia Dodonova, Mikhail Belyaev, Anna Tkachev, Dmitry Petrov, Leonid Zhukov
In this paper, we tackle a problem of predicting phenotypes from structural connectomes.