Related papers: Eff-GRot: Efficient and Generalizable Rotation Est…
Computational neuromorphic imaging (CNI) with event cameras offers advantages such as minimal motion blur and enhanced dynamic range, compared to conventional frame-based methods. Existing event-based radiance field rendering methods are…
The Gaussian splatting methods are getting popular. However, their loss function only contains the $\ell_1$ norm and the structural similarity between the rendered and input images, without considering the edges in these images. It is…
Image retrieval-based cross-view localization methods often lead to very coarse camera pose estimation, due to the limited sampling density of the database satellite images. In this paper, we propose a method to increase the accuracy of a…
Most existing methods for CRF estimation from a single image fail to handle general real images. For instance, EdgeCRF based on colour patches extracted from edges works effectively only when the presence of noise is insignificant, which is…
Learning based 6D object pose estimation methods rely on computing large intermediate pose representations and/or iteratively refining an initial estimation with a slow render-compare pipeline. This paper introduces a novel method we call…
Autonomous grasping of novel objects that are previously unseen to a robot is an ongoing challenge in robotic manipulation. In the last decades, many approaches have been presented to address this problem for specific robot hands. The…
In this paper, we investigate the inconsistency problem arising from observability mismatch that frequently occurs in nonlinear systems such as multi-robot cooperative localization and simultaneous localization and mapping. For a general…
This paper introduces a highly efficient algorithm capable of jointly estimating scale and rotation between two images with sub-pixel precision. Image alignment serves as a critical process for spatially registering images captured from…
Time series forecasting at scale presents significant challenges for modern prediction systems, particularly when dealing with large sets of synchronized series, such as in a global payment network. In such systems, three key challenges…
Transformer-based models have recently shown success in representation learning on graph-structured data beyond natural language processing and computer vision. However, the success is limited to small-scale graphs due to the drawbacks of…
This work aims at the precise and efficient computation of the x-ray projection of an image represented by a linear combination of general shifted basis functions that typically overlap. We achieve this with a suitable adaptation of ray…
Equivariant Graph Neural Networks (GNNs) have significantly advanced the modeling of 3D molecular structure by leveraging group representations. However, their message passing, heavily relying on Clebsch-Gordan tensor product convolutions,…
Grasp detection in a cluttered environment is still a great challenge for robots. Currently, the Transformer mechanism has been successfully applied to visual tasks, and its excellent ability of global context information extraction…
Transformer-based foundation models have achieved remarkable progress in tasks such as time-series forecasting and image segmentation. However, they frequently suffer from error accumulation in multivariate long-sequence prediction and…
Most man-made environments, such as urban and indoor scenes, consist of a set of parallel and orthogonal planar structures. These structures are approximated by the Manhattan world assumption, in which notion can be represented as a…
We present REMM, a rotation-equivariant framework for end-to-end multimodal image matching, which fully encodes rotational differences of descriptors in the whole matching pipeline. Previous learning-based methods mainly focus on extracting…
Manipulating arbitrary objects in unstructured environments is a significant challenge in robotics, primarily due to difficulties in determining an object's center of mass. This paper introduces U-GRAPH: Uncertainty-Guided Rotational Active…
We present a novel approach for the inverse problem in electrical impedance tomography based on regularized quadratic regression. Our contribution introduces a new formulation for the forward model in the form of a nonlinear integral…
Morden deep ensembles technique achieves strong uncertainty estimation performance by going through multiple forward passes with different models. This is at the price of a high storage space and a slow speed in the inference (test) time.…
We introduce \textit{SeismoGPT}, a transformer-based model for forecasting three-component seismic waveforms in the context of future gravitational wave detectors like the Einstein Telescope. The model is trained in an autoregressive…