Related papers: Deep Frequency-Aware Functional Maps for Robust Sh…
Pan-sharpening involves reconstructing missing high-frequency information in multi-spectral images with low spatial resolution, using a higher-resolution panchromatic image as guidance. Although the inborn connection with frequency domain,…
Existing deep trackers mainly use convolutional neural networks pre-trained for generic object recognition task for representations. Despite demonstrated successes for numerous vision tasks, the contributions of using pre-trained deep…
Prior to modern Earth observation technologies, historical maps provide a unique record of long-term urban transformation and offer a lens on the evolving identity of cities. However, extracting consistent and fine-grained change…
Methods that combine local and global features have recently shown excellent performance on multiple challenging deep image retrieval benchmarks, but their use of local features raises at least two issues. First, these local features simply…
High-definition maps (HD maps) are a key component of most modern self-driving systems due to their valuable semantic and geometric information. Unfortunately, building HD maps has proven hard to scale due to their cost as well as the…
Many imaging problems can be formulated as mapping problems. A general mapping problem aims to obtain an optimal mapping that minimizes an energy functional subject to the given constraints. Existing methods to solve the mapping problems…
We propose a lifelong 3D mapping framework that is modular, cloud-native by design and more importantly, works for both hand-held and robot-mounted 3D LiDAR mapping systems. Our proposed framework comprises of dynamic point removal,…
Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods used a subset of combinations of component functions and weight matrices within the random feature paradigm. We…
The depth completion task is a critical problem in autonomous driving, involving the generation of dense depth maps from sparse depth maps and RGB images. Most existing methods employ a spatial propagation network to iteratively refine the…
We propose neural network layers that explicitly combine frequency and image feature representations and show that they can be used as a versatile building block for reconstruction from frequency space data. Our work is motivated by the…
We present a novel method to provide efficient and highly detailed reconstructions. Inspired by wavelets, we learn a neural field that decompose the signal both spatially and frequency-wise. We follow the recent grid-based paradigm for…
Path loss prediction is a beneficial tool for efficient use of the radio frequency spectrum. Building on prior research on high-resolution map-based path loss models, this paper studies convolutional neural network input representations in…
A comprehensive framework for detection and characterization of overlapping intrinsic symmetry over 3D shapes is proposed. To identify prominent symmetric regions which overlap in space and vary in form, the proposed framework is decoupled…
Despite significant progress in deep learning-based optical flow methods, accurately estimating large displacements and repetitive patterns remains a challenge. The limitations of local features and similarity search patterns used in these…
Interpretation of deep learning remains a very challenging problem. Although the Class Activation Map (CAM) is widely used to interpret deep model predictions by highlighting object location, it fails to provide insight into the salient…
The graph fractional Fourier transform (GFRFT) applies a single global fractional order to all graph frequencies, which restricts its adaptability to diverse signal characteristics across the spectral domain. To address this limitation, in…
Spectral Graph Neural Networks (GNNs) are gaining attention for their ability to surpass the limitations of message-passing GNNs. They rely on supervision from downstream tasks to learn spectral filters that capture the graph signal's…
Flow map learning (FML), in conjunction with deep neural networks (DNNs), has shown promises for data driven modeling of unknown dynamical systems. A remarkable feature of FML is that it is capable of producing accurate predictive models…
Diffusion Map is a spectral dimensionality reduction technique which is able to uncover nonlinear submanifolds in high-dimensional data. And, it is increasingly applied across a wide range of scientific disciplines, such as biology,…
Deformable image registration establishes non-linear spatial correspondences between fixed and moving images. Deep learning-based deformable registration methods have been widely studied in recent years due to their speed advantage over…