Related papers: sZoom: A Framework for Automatic Zoom into High Re…
MLLMs require high-resolution visual inputs for fine-grained tasks like document understanding and dense scene perception. However, current global resolution scaling paradigms indiscriminately flood the quadratic self-attention mechanism…
In cinema, large camera lenses create beautiful shallow depth of field (DOF), but make focusing difficult and expensive. Accurate cinema focus usually relies on a script and a person to control focus in realtime. Casual videographers often…
Videos are a popular media form, where online video streaming has recently gathered much popularity. In this work, we propose a novel method of real-time video stabilization - transforming a shaky video to a stabilized video as if it were…
In modern intelligent video surveillance systems, automatic anomaly detection through computer vision analytics plays a pivotal role which not only significantly increases monitoring efficiency but also reduces the burden on live…
The goal of video segmentation is to turn video data into a set of concrete motion clusters that can be easily interpreted as building blocks of the video. There are some works on similar topics like detecting scene cuts in a video, but…
Despite advancements in user-guided video segmentation, extracting complex objects consistently for highly complex scenes is still a labor-intensive task, especially for production. It is not uncommon that a majority of frames need to be…
Video summarization is among challenging tasks in computer vision, which aims at identifying highlight frames or shots over a lengthy video input. In this paper, we propose an novel attention-based framework for video summarization with…
This paper introduces a framework for super-resolution of scalable video based on compressive sensing and sparse representation of residual frames in reconnaissance and surveillance applications. We exploit efficient compressive sampling…
The growing demand for surveillance in public spaces presents significant challenges due to the shortage of human resources. Current AI-based video surveillance systems heavily rely on core computer vision models that require extensive…
A framework is proposed to assess the safety of maintenance work zones in a timely manner, show whether there are safety hazards, whether adjustments need to be made and how to adjust it. By means of advanced data acquisition technologies…
We developed a real-time, high-quality semi-supervised video object segmentation algorithm. Its accuracy is on par with the most accurate, time-consuming online-learning model, while its speed is similar to the fastest template-matching…
Detection in large-scale scenes is a challenging problem due to small objects and extreme scale variation. It is essential to focus on the image regions of small objects. In this paper, we propose a novel Adaptive Zoom (AdaZoom) network as…
Humans are remarkably efficient at forming spatial understanding from just a few visual observations. When browsing real estate or navigating unfamiliar spaces, they intuitively select a small set of views that summarize the spatial layout.…
Segmenting foreground object from a video is a challenging task because of the large deformations of the objects, occlusions, and background clutter. In this paper, we propose a frame-by-frame but computationally efficient approach for…
We introduce GaussianZoom, a generative zoom-in 3D reconstruction system with an iterative progressive framework that combines geometry-consistent scene modeling and multi-scale semantic reasoning to enable high-fidelity extreme zoom-in…
With ever increasing computing power and data storage capacity, the potential for large digital video libraries is growing rapidly.However, the massive use of video for the moment is limited by its opaque characteristics. Indeed, a user who…
The problem of action recognition involves locating the action in the video, both over time and spatially in the image. The dominant current approaches use supervised learning to solve this problem, and require large amounts of annotated…
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…
In this work, we propose a novel procedure for video super-resolution, that is the recovery of a sequence of high-resolution images from its low-resolution counterpart. Our approach is based on a "sequential" model (i.e., each…
The online reconstruction of dynamic scenes from multi-view streaming videos faces significant challenges in training, rendering and storage efficiency. Harnessing superior learning speed and real-time rendering capabilities, 3D Gaussian…