arXiv research

PointGMM learns hGMMs from point clouds for 3D shape representation.

New shape representation for airfoils improves design and manufacturing.

This work characterizes how data augmentation shapes neural representations.

Generative modeling of 3D shapes has become an important problem due to its relevance to many applications across Computer Vision, Graphics, and VR. In this paper we build upon recently introduced 3D mesh-convolutional Variational AutoEncoders which have shown great promise for learning rich representations of deformab…

Bézier-GAN optimizes airfoil design by reducing shape complexity.

The paper studies dynamic star-shaped risk measures and their representation.

SVarM uses varifold representations for shape classification and regression.

The success of various applications including robotics, digital content creation, and visualization demand a structured and abstract representation of the 3D world from limited sensor data. Inspired by the nature of human perception of 3D shapes as a collection of simple parts, we explore such an abstract shape represe…

The paper characterizes law-invariant star-shaped risk measures.

Unified understanding of neural representation similarity measures.

New set-valued star-shaped risk measures introduced for better risk assessment.

Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes. Some recent studies suggest a more important role of image textures. We here put these conflicting hypotheses to a quantitative test by evaluating CNNs and human observers on…

New method estimates shape distance in neural representations with limited data.

Left atrium shape has been shown to be an independent predictor of recurrence after atrial fibrillation (AF) ablation. Shape-based representation is imperative to such an estimation process, where correspondence-based representation offers the most flexibility and ease-of-computation for population-level shape statisti…

Fine shape of local compacta represented by ordinary maps.

We present a novel, log-radius profile representation for convex curves and define a new operation for combining the shape features of curves. Unlike the standard, angle profile-based methods, this operation accurately combines the shape features in a visually intuitive manner. This method have implications in shape an…

Representing shapes as level sets of neural networks has been recently proved to be useful for different shape analysis and reconstruction tasks. So far, such representations were computed using either: (i) pre-computed implicit shape representations; or (ii) loss functions explicitly defined over the neural level sets…

New deep learning method preserves orientation in shape matching.

Direct proof of Alexander polynomial scaling for L-shaped representations.

VQShape learns interpretable time-series representations and achieves comparable performance to specialist models.

LIMP learns latent shapes with metric preservation, improving generative models.

Self-supervised reward prediction improves RL in sparse reward settings.

New method for partial matching of shapes with Varifolds.

This paper connects monetary and star-shaped risk measures by showing their equivalence under certain conditions.

ES-VAE models skeletal pose trajectories by removing nuisance factors.

Fine shape theory extends strong shape to noncompact metrizable spaces.

Convolutional Neural Networks (CNNs) have become the state-of-the-art method to learn from image data. However, recent research shows that they may include a texture and colour bias in their representation, contrary to the intuition that they learn the shapes of the image content and to human biological learning. Thus,…

Describing shapes by suitable measures in object segmentation, as proposed in [24], allows to combine the advantages of the representations as parametrized contours and indicator functions. The pseudo-Riemannian structure of optimal transport can be used to model shapes in ways similar as with contours, while the Kanto…

We consider the problem of modelling noisy but highly symmetric shapes that can be viewed as hierarchies of whole-part relationships in which higher level objects are composed of transformed collections of lower level objects. To this end, we propose the stochastic wreath process, a fully generative probabilistic model…

Recent progress in deep generative models has led to tremendous breakthroughs in image generation. However, while existing models can synthesize photorealistic images, they lack an understanding of our underlying 3D world. We present a new generative model, Visual Object Networks (VON), synthesizing natural images of o…

The paper presents a method for analyzing shape graphs using specific features.

New method learns shape correspondences robustly from raw geometry.

Let $M$ be a most singular orbit of the isotropy representation of a simple symmetric space. Let $(ν_i, Φ_i)$ be an irreducible factor of the normal holonomy representation $(ν_pM, Φ(p))$. We prove that there exists a basis of a section $Σ_i\subset ν_i$ of $Φ_i$ such that the corresponding shape operators have rational…

Paper develops a new method to analyze 3D tree-like objects.

In a previous paper, we parametrized boundary-unipotent representations of a 3-manifold group into SL(n,C) using Ptolemy coordinates, which were inspired by A-coordinates on higher Teichmüller space due to Fock and Goncharov. In this paper, we parametrize representations into PGL(n,C) using shape coordinates which are …

We propose a data-driven 3D shape design method that can learn a generative model from a corpus of existing designs, and use this model to produce a wide range of new designs. The approach learns an encoding of the samples in the training corpus using an unsupervised variational autoencoder-decoder architecture, withou…

This study improves sentence embeddings from BERT models.

Paper analyzes shapes of brain arterial networks using statistical methods.

In this paper, we address the problem of orientation that naturally arises when representing shapes like curves or surfaces as currents. In the field of computational anatomy, the framework of currents has indeed proved very efficient to model a wide variety of shapes. However, in such approaches, orientation of shapes…

FineHand learns hand shapes for better ASL recognition.

Study S-shaped utility maximization with VaR constraint and unobservable drift.

Recognizing facial expressions from static images or video sequences is a widely studied but still challenging problem. The recent progresses obtained by deep neural architectures, or by ensembles of heterogeneous models, have shown that integrating multiple input representations leads to state-of-the-art results. In p…

The paper finds formulas for special surface shapes in 3D space.

Analyze and predict complex 3D shape deformations using LSTM autoencoders and oriented bounding boxes.

In some sense, the world is composed of shapes and words, of continuous things and discrete things. The recognition and study of continuous objects in the form of shapes occupies a significant part of the effort of unraveling many geometric questions. Shapes can be rep- resented with great generality by objects called …

This paper introduces the concept of functional current as a mathematical framework to represent and treat functional shapes, i.e. sub-manifold supported signals. It is motivated by the growing occurrence, in medical imaging and computational anatomy, of what can be described as geometrico-functional data, that is a da…

This paper introduces a new shape-based image reconstruction technique applicable to a large class of imaging problems formulated in a variational sense. Given a collection of shape priors (a shape dictionary), we define our problem as choosing the right elements and geometrically composing them through basic set opera…

The paper uses 3D shapes to reveal sundial design adjustments based on latitude.