Related papers: GPU-accelerated SIFT-aided source identification o…
Dataset distillation aims to synthesize compact yet informative datasets that allow models trained on them to achieve performance comparable to training on the full dataset. While this approach has shown promising results for image data,…
Shift-and-add is an approach employed to mitigate the phenomenon of resolution degradation in images acquired through a turbulent medium. Using this technique, a large number of consecutive short exposures is registered below the coherence…
We study self-supervised video representation learning, which is a challenging task due to 1) lack of labels for explicit supervision; 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video…
Applying single image Monocular Depth Estimation (MDE) models to video sequences introduces significant temporal instability and flickering artifacts. We propose a novel approach that adapts any state-of-the-art image-based (depth)…
Structural parameters are normally extracted from observed galaxies by fitting analytic light profiles to the observations. Obtaining accurate fits to high-resolution images is a computationally expensive task, requiring many model…
The integral image, an intermediate image representation, has found extensive use in multi-scale local feature detection algorithms, such as Speeded-Up Robust Features (SURF), allowing fast computation of rectangular features at constant…
The ability to detect fragments of deleted image files and to reconstruct these image files from all available fragments on disk is a key activity in the field of digital forensics. Although reconstruction of image files from the file…
Prevailing video frame interpolation algorithms, that generate the intermediate frames from consecutive inputs, typically rely on complex model architectures with heavy parameters or large delay, hindering them from diverse real-time…
Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur. Previous approaches exploit to propagate and aggregate features across…
LU factorization for sparse matrices is the most important computing step for many engineering and scientific computing problems such as circuit simulation. But parallelizing LU factorization with the Graphic Processing Units (GPU) still…
Recently, flow-based frame interpolation methods have achieved great success by first modeling optical flow between target and input frames, and then building synthesis network for target frame generation. However, above cascaded…
Video fusion is a process that combines visual data from different sensors to obtain a single composite video preserving the information of the sources. The availability of a system, enhancing human ability to perceive the observed…
Motion, as the uniqueness of a video, has been critical to the development of video understanding models. Modern deep learning models leverage motion by either executing spatio-temporal 3D convolutions, factorizing 3D convolutions into…
In image fusion, images obtained from different sensors are fused to generate a single image with enhanced information. In recent years, state-of-the-art methods have adopted Convolution Neural Networks (CNNs) to encode meaningful features…
Embedded vision systems need efficient and robust image processing algorithms to perform real-time, with resource-constrained hardware. This research investigates image processing algorithms, specifically edge detection, corner detection,…
Temporally consistent dense video annotations are scarce and hard to collect. In contrast, image segmentation datasets (and pre-trained models) are ubiquitous, and easier to label for any novel task. In this paper, we introduce a method to…
Video summarization plays an important role in selecting keyframe for understanding a video. Traditionally, it aims to find the most representative and diverse contents (or frames) in a video for short summaries. Recently, query-conditioned…
Adversarial attacks expose a fundamental vulnerability in modern deep vision models by exploiting their dependence on dense, pixel-level representations that are highly sensitive to imperceptible perturbations. Traditional defense…
The slow inference process of image diffusion models significantly degrades interactive user experiences. To address this, we introduce Diffusion Preview, a novel paradigm employing rapid, low-step sampling to generate preliminary outputs…
Object detection and recognition algorithms using deep convolutional neural networks (CNNs) tend to be computationally intensive to implement. This presents a particular challenge for embedded systems, such as mobile robots, where the…