Related papers: Eff-GRot: Efficient and Generalizable Rotation Est…
Various recent methods attempt to implement rotation-invariant 3D deep learning by replacing the input coordinates of points with relative distances and angles. Due to the incompleteness of these low-level features, they have to undertake…
We present a novel usage of Transformers to make image classification interpretable. Unlike mainstream classifiers that wait until the last fully connected layer to incorporate class information to make predictions, we investigate a…
Global localization plays a critical role in many robot applications. LiDAR-based global localization draws the community's focus with its robustness against illumination and seasonal changes. To further improve the localization under large…
Graph Transformers (GTs) have shown strong empirical performance, yet current architectures vary widely in their use of attention mechanisms, positional embeddings (PEs), and expressivity. Existing expressivity results are often tied to…
Transformers have achieved remarkable results in single-image super-resolution (SR). However, the challenge of balancing model performance and complexity has hindered their application in lightweight SR (LSR). To tackle this challenge, we…
The shifted frequency-based electromagnetic transient (SFEMT) simulation has greatly improved the computational efficiency of traditional electromagnetic transient (EMT) simulation for the ac grid. This letter proposes a novel interface for…
Modeling sparse and dense image matching within a unified functional correspondence model has recently attracted increasing research interest. However, existing efforts mainly focus on improving matching accuracy while ignoring its…
We aim at estimating the fundamental matrix in two views from five correspondences of rotation invariant features obtained by e.g.\ the SIFT detector. The proposed minimal solver first estimates a homography from three correspondences…
Rotation invariance is essential for precise, object-level segmentation in UAV aerial imagery, where targets can have arbitrary orientations and exhibit fine-scale details. Conventional segmentation architectures like U-Net rely on…
Early-exit neural networks enable adaptive inference by allowing predictions at intermediate layers, reducing computational cost. However, early exits often lack interpretability and may focus on different features than deeper layers,…
Neural Radiance Fields (NeRF) have transformed novel view synthesis by modeling scene-specific volumetric representations directly from images. While generalizable NeRF models can generate novel views across unknown scenes by learning…
It is customary to perform analysis of the Earth's rotation in two steps: first, to present results of estimation of the Earth orientation parameters in the form of time series based on a simplified model of variations of the Earth's…
Fast methods for convolution and correlation underlie a variety of applications in computer vision and graphics, including efficient filtering, analysis, and simulation. However, standard convolution and correlation are inherently limited…
Recent advances in generative image restoration (IR) have demonstrated impressive results. However, these methods are hindered by their substantial size and computational demands, rendering them unsuitable for deployment on edge devices.…
Objective: In this work, we propose a framework for differentiable forward and back-projector that enables scalable, accurate, and memory-efficient gradient computation for rigid motion estimation tasks. Methods: Unlike existing approaches…
This paper proposes to use Fast Fourier Transformation-based U-Net (a refined fully convolutional networks) and perform image convolution in neural networks. Leveraging the Fast Fourier Transformation, it reduces the image convolution costs…
Recent neural heuristics for the Vehicle Routing Problem (VRP) primarily rely on node coordinates as input, which may be less effective in practical scenarios where real cost metrics-such as edge-based distances-are more relevant. To…
Gaze estimation is a crucial task in computer vision, however, existing methods suffer from high computational costs, which limit their practical deployment in resource-limited environments. In this paper, we propose a novel lightweight…
Predicting multimodal future behavior of traffic participants is essential for robotic vehicles to make safe decisions. Existing works explore to directly predict future trajectories based on latent features or utilize dense goal candidates…
With the ever increasing application of Convolutional Neural Networks to customer products the need emerges for models to efficiently run on embedded, mobile hardware. Slimmer models have therefore become a hot research topic with various…