FacadeNet: Conditional Facade Synthesis via Selective Editing

no code implementations • 2 Nov 2023 • Yiangos Georgiou, Marios Loizou, Tom Kelly, Melinos Averkiou

We introduce FacadeNet, a deep learning approach for synthesizing building facade images from diverse viewpoints.

PriFit: Learning to Fit Primitives Improves Few Shot Point Cloud Segmentation

1 code implementation • 27 Dec 2021 • Gopal Sharma, Bidya Dash, Aruni RoyChowdhury, Matheus Gadelha, Marios Loizou, Liangliang Cao, Rui Wang, Erik Learned-Miller, Subhransu Maji, Evangelos Kalogerakis

We present PriFit, a semi-supervised approach for label-efficient learning of 3D point cloud segmentation networks.

Few-Shot Learning Point Cloud Segmentation +2

BuildingNet: Learning to Label 3D Buildings

1 code implementation • ICCV 2021 • Pratheba Selvaraju, Mohamed Nabail, Marios Loizou, Maria Maslioukova, Melinos Averkiou, Andreas Andreou, Siddhartha Chaudhuri, Evangelos Kalogerakis

We introduce BuildingNet: (a) a large-scale dataset of 3D building models whose exteriors are consistently labeled, (b) a graph neural network that labels building meshes by analyzing spatial and structural relations of their geometric primitives.

2k 3D Building Mesh Labeling +1

Learning Part Boundaries from 3D Point Clouds

1 code implementation • 15 Jul 2020 • Marios Loizou, Melinos Averkiou, Evangelos Kalogerakis

We present a method that detects boundaries of parts in 3D shapes represented as point clouds.

Cross-Shape Attention for Part Segmentation of 3D Point Clouds

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.

3D Semantic Segmentation Retrieval +1