Related papers: CineFilter: Unsupervised Filtering for Real Time A…

Predicting future frames of a video sequence has been a problem of high interest in the field of Computer Vision as it caters to a multitude of applications. The ability to predict, anticipate and reason about future events is the essence…

In recent years, advances in Artificial Intelligence have significantly impacted computer science, particularly in the field of computer vision, enabling solutions to complex problems such as video frame prediction. Video frame prediction…

We aim to provide a general framework of for computational photography that recovers the real scene from imperfect images, via the Deep Nonparametric Convexified Filtering (DNCF). It is consists of a nonparametric deep network to resemble…

Taking photographs ''in-the-wild'' is often hindered by fence obstructions that stand between the camera user and the scene of interest, and which are hard or impossible to avoid. De-fencing is the algorithmic process of automatically…

In the Internet, ubiquitous presence of redundant, unedited, raw videos has made video summarization an important problem. Traditional methods of video summarization employ a heuristic set of hand-crafted features, which in many cases fail…

Conventionally, convolutional neural networks (CNNs) process different images with the same set of filters. However, the variations in images pose a challenge to this fashion. In this paper, we propose to generate sample-specific filters…

In the past several years, road anomaly segmentation is actively explored in the academia and drawing growing attention in the industry. The rationale behind is straightforward: if the autonomous car can brake before hitting an anomalous…

Trajectory prediction for autonomous driving must continuously reason the motion stochasticity of road agents and comply with scene constraints. Existing methods typically rely on one-stage trajectory prediction models, which condition…

Lane changing and obstacle avoidance are one of the most important tasks in automated cars. To date, many algorithms have been suggested that are generally based on path trajectory or reinforcement learning approaches. Although these…

With advancements in video generative AI models (e.g., SORA), creators are increasingly using these techniques to enhance video previsualization. However, they face challenges with incomplete and mismatched AI workflows. Existing methods…

Optimization-based filtering smoothes an image by minimizing a fidelity function and simultaneously preserves edges by exploiting a sparse norm penalty over gradients. It has obtained promising performance in practical problems, such as…

Correlation filters are special classifiers designed for shift-invariant object recognition, which are robust to pattern distortions. The recent literature shows that combining a set of sub-filters trained based on a single or a small group…

Motion blur is a fundamental problem in computer vision as it impacts image quality and hinders inference. Traditional deblurring algorithms leverage the physics of the image formation model and use hand-crafted priors: they usually produce…

Given the vast amounts of video available online, and recent breakthroughs in object detection with static images, object detection in video offers a promising new frontier. However, motion blur and compression artifacts cause substantial…

MPC (Model predictive control)-based motion planning and trajectory generation are essential in applications such as unmanned aerial vehicles, robotic manipulators, and rocket control. However, the real-time implementation of such…

Multi-step prediction models, such as diffusion and rectified flow models, have emerged as state-of-the-art solutions for generation tasks. However, these models exhibit higher latency in sampling new frames compared to single-step methods.…

The deep convolutional neural network (DCNN) in computer vision has given promising results. It is widely applied in many areas, from medicine, agriculture, self-driving car, biometric system, and almost all computer vision-based…

Video anomaly detection in surveillance systems with only video-level labels (i.e. weakly-supervised) is challenging. This is due to, (i) the complex integration of human and scene based anomalies comprising of subtle and sharp…

Due to the problem of performance constraints of unsupervised video object detection, its large-scale application is limited. In response to this pain point, we propose another excellent method to solve this problematic point. By…

Conventional cameras generate a lot of data that can be challenging to process in resource-constrained applications. Usually, cameras generate data streams on the order of the number of pixels in the image. However, most of this captured…