Related papers: Learning Probabilistic Coordinate Fields for Robus…

Representing token embeddings as probability distributions over learned manifolds allows for more flexible contextual inference, reducing representational rigidity while enhancing semantic granularity. Comparative evaluations demonstrate…

We present a novel feature matching algorithm that systematically utilizes the geometric properties of features such as position, scale, and orientation, in addition to the conventional descriptor vectors. In challenging scenes with the…

In this paper, we present a framework for computing dense keypoint correspondences between images under strong scene appearance changes. Traditional methods, based on nearest neighbour search in the feature descriptor space, perform poorly…

Domain adaptive image retrieval includes single-domain retrieval and cross-domain retrieval. Most of the existing image retrieval methods only focus on single-domain retrieval, which assumes that the distributions of retrieval databases and…

Two types of probabilistic maps are popular in the mobile robotics literature: occupancy grids and geometric maps. Occupancy grids have the advantages of simplicity and speed, but they represent only a restricted class of maps and they make…

This paper addresses the challenge of Neural Field (NeF) generalization, where models must efficiently adapt to new signals given only a few observations. To tackle this, we propose Geometric Neural Process Fields (G-NPF), a probabilistic…

Accurately predicting future pedestrian trajectories is crucial across various domains. Due to the uncertainty in future pedestrian trajectories, it is important to learn complex spatio-temporal representations in multi-agent scenarios. To…

Local features e.g. SIFT and its affine and learned variants provide region-to-region rather than point-to-point correspondences. This has recently been exploited to create new minimal solvers for classical problems such as homography,…

Geometric shape classification of vector polygons remains a challenging task in spatial analysis. Previous studies have primarily focused on deep learning approaches for rasterized vector polygons, while the study of discrete polygon…

The convex feasibility problem (CFP) is to find a feasible point in the intersection of finitely many convex and closed sets. If the intersection is empty then the CFP is inconsistent and a feasible point does not exist. However,…

In this work we target the problem of estimating accurately localised correspondences between a pair of images. We adopt the recent Neighbourhood Consensus Networks that have demonstrated promising performance for difficult correspondence…

Coarse-graining (CG) of molecular simulations simplifies the particle representation by grouping selected atoms into pseudo-beads and drastically accelerates simulation. However, such CG procedure induces information losses, which makes…

We propose a method for estimating the 6DoF pose of a rigid object with an available 3D model from a single RGB image. Unlike classical correspondence-based methods which predict 3D object coordinates at pixels of the input image, the…

Scene coordinate regression has become an essential part of current camera re-localization methods. Different versions, such as regression forests and deep learning methods, have been successfully applied to estimate the corresponding…

CoVariance Neural Networks (VNNs) perform convolutions on the graph determined by the covariance matrix of the data, which enables expressive and stable covariance-based learning. However, covariance matrices are typically dense, fail to…

Convolutional neural nets (convnets) trained from massive labeled datasets have substantially improved the state-of-the-art in image classification and object detection. However, visual understanding requires establishing correspondence on…

Despite significant progress of deep learning in recent years, state-of-the-art semantic matching methods still rely on legacy features such as SIFT or HoG. We argue that the strong invariance properties that are key to the success of…

Probability distribution modeling is the basis for most competitive methods for lossless coding of screen content. One such state-of-the-art method is known as soft context formation (SCF). For each pixel to be encoded, a probability…

This paper addresses the problem of handling spatial misalignments due to camera-view changes or human-pose variations in person re-identification. We first introduce a boosting-based approach to learn a correspondence structure which…

In optical communications, logical bits are encoded in physical degrees-of-freedom (DoFs) of the electromagnetic field. Consequently, optical scattering in a communications channel compromises the information transfer. In the…