Browsing by Author "Loizou, Marios"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Cross-Shape Attention for Part Segmentation of 3D Point Clouds
    (The Eurographics Association and John Wiley & Sons Ltd., 2023) Loizou, Marios; Garg, Siddhant; Petrov, Dmitry; Averkiou, Melinos; Kalogerakis, Evangelos; Memari, Pooran; Solomon, Justin
    We present a deep learning method that propagates point-wise feature representations across shapes within a collection for the purpose of 3D shape segmentation. We propose a cross-shape attention mechanism to enable interactions between a shape's point-wise features and those of other shapes. 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. Our method also proposes a shape retrieval measure to select suitable shapes for crossshape attention operations for each test shape. Our experiments demonstrate that our approach yields state-of-the-art results in the popular PartNet dataset.
  • Thumbnail Image
    Item
    PriFit: Learning to Fit Primitives Improves Few Shot Point Cloud Segmentation
    (The Eurographics Association and John Wiley & Sons Ltd., 2022) Sharma, Gopal; Dash, Bidya; RoyChowdhury, Aruni; Gadelha, Matheus; Loizou, Marios; Cao, Liangliang; Wang, Rui; Learned-Miller, Erik G.; Maji, Subhransu; Kalogerakis, Evangelos; Campen, Marcel; Spagnuolo, Michela
    We present PRIFIT, a semi-supervised approach for label-efficient learning of 3D point cloud segmentation networks. PRIFIT combines geometric primitive fitting with point-based representation learning. Its key idea is to learn point representations whose clustering reveals shape regions that can be approximated well by basic geometric primitives, such as cuboids and ellipsoids. The learned point representations can then be re-used in existing network architectures for 3D point cloud segmentation, and improves their performance in the few-shot setting. According to our experiments on the widely used ShapeNet and PartNet benchmarks, PRIFIT outperforms several state-of-the-art methods in this setting, suggesting that decomposability into primitives is a useful prior for learning representations predictive of semantic parts. We present a number of ablative experiments varying the choice of geometric primitives and downstream tasks to demonstrate the effectiveness of the method.