Related papers: Efficient Spatially Adaptive Convolution and Corre…
In sparse coding, we attempt to extract features of input vectors, assuming that the data is inherently structured as a sparse superposition of basic building blocks. Similarly, neural networks perform a given task by learning features of…
The Discriminative Correlation Filter (CF) uses a circulant convolution operation to provide several training samples for the design of a classifier that can distinguish the target from the background. The filter design may be interfered by…
Spatial data display correlation between observations collected at neighboring locations. Generally, machine and deep learning methods either do not account for this correlation or do so indirectly through correlated features and thereby…
State-of-the-art super-resolution (SR) algorithms require significant computational resources to achieve real-time throughput (e.g., 60Mpixels/s for HD video). This paper introduces FAST (Free Adaptive Super-resolution via Transfer), a…
Convolutional neural networks excel in a number of computer vision tasks. One of their most crucial architectural elements is the effective receptive field size, that has to be manually set to accommodate a specific task. Standard solutions…
While 360{\deg} cameras offer tremendous new possibilities in vision, graphics, and augmented reality, the spherical images they produce make core feature extraction non-trivial. Convolutional neural networks (CNNs) trained on images from…
This work proposes a novel framework for visual tracking based on the integration of an iterative particle filter, a deep convolutional neural network, and a correlation filter. The iterative particle filter enables the particles to correct…
Correlation filters take advantage of specific properties in the Fourier domain allowing them to be estimated efficiently: O(NDlogD) in the frequency domain, versus O(D^3 + ND^2) spatially where D is signal length, and N is the number of…
Modern convolutional neural networks apply the same operations on every pixel in an image. However, not all image regions are equally important. To address this inefficiency, we propose a method to dynamically apply convolutions conditioned…
Image forensics, aiming to ensure the authenticity of the image, has made great progress in dealing with common image manipulation such as copy-move, splicing, and inpainting in the past decades. However, only a few researchers pay…
Deep convolutional neural networks are hindered by training instability and feature redundancy towards further performance improvement. A promising solution is to impose orthogonality on convolutional filters. We develop an efficient…
This paper tackles the problem of dynamic scene deblurring. Although end-to-end fully convolutional designs have recently advanced the state-of-the-art in non-uniform motion deblurring, their performance-complexity trade-off is still…
The efficient realization of linear space-variant (non-convolution) filters is a challenging computational problem in image processing. In this paper, we demonstrate that it is possible to filter an image with a Gaussian-like elliptic…
Extending the translation equivariance property of convolutional neural networks to larger symmetry groups has been shown to reduce sample complexity and enable more discriminative feature learning. Further, exploiting additional symmetries…
Correlation Filters (CFs) have recently demonstrated excellent performance in terms of rapidly tracking objects under challenging photometric and geometric variations. The strength of the approach comes from its ability to efficiently learn…
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…
Object tracking is challenging as target objects often undergo drastic appearance changes over time. Recently, adaptive correlation filters have been successfully applied to object tracking. However, tracking algorithms relying on highly…
The concept of sparsity has been extensively applied for regularization in image reconstruction. Typically, sparsifying transforms are either pre-trained on ground-truth images or adaptively trained during the reconstruction. Thereby,…
The use of laser guide stars in astronomical adaptive optics results in elongated Shack-Hartmann wavefront sensor image patterns. Image correlation techniques can be used to determine local wavefront slope by correlating each sub-aperture…
Very recently, Window-based Transformers, which computed self-attention within non-overlapping local windows, demonstrated promising results on image classification, semantic segmentation, and object detection. However, less study has been…