Related papers: HodgeFormer: Transformers for Learnable Operators …

3D morphable models are widely used for the shape representation of an object class in computer vision and graphics applications. In this work, we focus on deep 3D morphable models that directly apply deep learning on 3D mesh data with a…

Deformation component analysis is a fundamental problem in geometry processing and shape understanding. Existing approaches mainly extract deformation components in local regions at a similar scale while deformations of real-world objects…

Transformer model architectures have become an indispensable staple in deep learning lately for their effectiveness across a range of tasks. Recently, a surge of "X-former" models have been proposed which improve upon the original…

Most modern deep learning-based multi-view 3D reconstruction techniques use RNNs or fusion modules to combine information from multiple images after independently encoding them. These two separate steps have loose connections and do not…

Let $M^n$ be a compact orientable smooth Riemannian submanifold of dimension $n\geq 3$ in $\mathbb R^d$. We construct a family of deformed Hodge Laplacians $\Delta_t^*$, $t>0$, acting on differential forms and defined through the extrinsic…

Images acquired in hazy conditions have degradations induced in them. Dehazing such images is a vexed and ill-posed problem. Scores of prior-based and learning-based approaches have been proposed to mitigate the effect of haze and generate…

Hypergraph Convolutional Neural Networks (HGCNNs) have demonstrated their potential in modeling high-order relations preserved in graph-structured data. However, most existing convolution filters are localized and determined by the…

Most approaches for semantic segmentation use only information from color cameras to parse the scenes, yet recent advancements show that using depth data allows to further improve performances. In this work, we focus on transformer-based…

Partial differential equations (PDEs) are fundamental for modeling complex physical systems, yet classical numerical solvers face prohibitive computational costs in high-dimensional and multi-scale regimes. While Transformer-based neural…

Transformer architectures have emerged as promising deep learning (DL) tools for modeling complex sequence-to-sequence interactions in channel decoding. However, current transformer-based decoders for error correction codes (ECCs)…

Transformers have become prevalent in computer vision due to their performance and flexibility in modelling complex operations. Of particular significance is the 'cross-attention' operation, which allows a vector representation (e.g. of an…

Transformer architecture has emerged to be successful in a number of natural language processing tasks. However, its applications to medical vision remain largely unexplored. In this study, we present UTNet, a simple yet powerful hybrid…

Since the Transformer architecture was introduced in 2017 there has been many attempts to bring the self-attention paradigm in the field of computer vision. In this paper we propose a novel self-attention module that can be easily…

Polygonal meshes have become the standard for discretely approximating 3D shapes, thanks to their efficiency and high flexibility in capturing non-uniform shapes. This non-uniformity, however, leads to irregularity in the mesh structure,…

HyperGraph Convolutional Neural Networks (HGCNNs) have demonstrated their potential in modeling high-order relations preserved in graph structured data. However, most existing convolution filters are localized and determined by the…

Hyperspectral image classification (HSIC) has gained significant attention because of its potential in analyzing high-dimensional data with rich spectral and spatial information. In this work, we propose the Differential Spatial-Spectral…

Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of elements of the set,…

Computer-aided medical image segmentation has been applied widely in diagnosis and treatment to obtain clinically useful information of shapes and volumes of target organs and tissues. In the past several years, convolutional neural network…

Over the past decade, Deep Convolutional Neural Networks have been widely adopted for medical image segmentation and shown to achieve adequate performance. However, due to the inherent inductive biases present in the convolutional…

Sparse Mixture-of-Experts (MoE) layers route tokens through a handful of experts, and learning-free compression of these layers reduces inference cost without retraining. A subtle obstruction blocks every existing compressor in this family:…