相关论文: Online Algorithms for Factorization-Based Structur…

State-of-the-art video deblurring methods are capable of removing non-uniform blur caused by unwanted camera shake and/or object motion in dynamic scenes. However, most existing methods are based on batch processing and thus need access to…

Integrating deep learning with latent state space models has the potential to yield temporal models that are powerful, yet tractable and interpretable. Unfortunately, current models are not designed to handle missing data or multiple data…

Target tracking and trajectory modeling have important applications in surveillance video analysis and have received great attention in the fields of road safety and community security. In this work, we propose a lightweight real-time video…

In this article we present an emulation strategy for one-loop matrix elements. This strategy is based on the factorisation properties of matrix elements and is an extension of the work presented in arXiv:2107.06625. We show that a…

We propose an online 3D semantic segmentation method that incrementally reconstructs a 3D semantic map from a stream of RGB-D frames. Unlike offline methods, ours is directly applicable to scenarios with real-time constraints, such as…

Multiresolution analysis and matrix factorization are foundational tools in computer vision. In this work, we study the interface between these two distinct topics and obtain techniques to uncover hierarchical block structure in symmetric…

Automatic reconstruction of 3D models from images using multi-view Structure-from-Motion methods has been one of the most fruitful outcomes of computer vision. These advances combined with the growing popularity of Micro Aerial Vehicles as…

Non-negative Matrix Factorization (NMF) asks to decompose a (entry-wise) non-negative matrix into the product of two smaller-sized nonnegative matrices, which has been shown intractable in general. In order to overcome this issue, the…

We investigate a general matrix factorization for deviance-based data losses, extending the ubiquitous singular value decomposition beyond squared error loss. While similar approaches have been explored before, our method leverages…

Controlling the manner in which a character moves in a real-time animation system is a challenging task with useful applications. Existing style transfer systems require access to a reference content motion clip, however, in real-time…

Representing 3D shape deformations by linear models in high-dimensional space has many applications in computer vision and medical imaging, such as shape-based interpolation or segmentation. Commonly, using Principal Components Analysis a…

Studying the factorization theory of numerical monoids relies on understanding several important factorization invariants, including length sets, delta sets, and $\omega$-primality. While progress in this field has been accelerated by the…

Compositional video generation aims to synthesize multiple instances with diverse appearance and motion. However, current approaches mainly focus on binding semantics, neglecting to understand diverse motion categories specified in prompts.…

Existing deep methods produce highly accurate 3D reconstructions in stereo and multiview stereo settings, i.e., when cameras are both internally and externally calibrated. Nevertheless, the challenge of simultaneous recovery of camera poses…

This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and…

Expanding reinforcement learning (RL) to offline domains generates promising prospects, particularly in sectors where data collection poses substantial challenges or risks. Pivotal to the success of transferring RL offline is mitigating…

We present a new algorithm to decompose generic spinor polynomials into linear factors. Spinor polynomials are certain polynomials with coefficients in the geometric algebra of dimension three that parametrize rational conformal motions.…

Designing a technique for the automatic analysis of different actions in videos in order to detect the presence of interested activities is of high significance nowadays. In this paper, we explore a robust and dynamic appearance technique…

The fast assembling of stiffness and mass matrices is a key issue in isogeometric analysis, particularly if the spline degree is increased. We present two algorithms based on the idea of sum factorization, one for matrix assembling and one…

Dynamic graph algorithms have seen significant theoretical advancements, but practical evaluations often lag behind. This work bridges the gap between theory and practice by engineering and empirically evaluating recently developed…