相关论文: Prediction-assistant Frame Super-Resolution for Vi…

Streaming video generation, as one fundamental component in interactive world models and neural game engines, aims to generate high-quality, low-latency, and temporally coherent long video streams. However, most existing work suffers from…

Video on Demand system over the wireless mobile network is a system that provides video services to mobile clients.The main problem with these systems is the high service delay where the mobile clients have to wait to view their favorite…

Video stabilization is essential for improving visual quality of shaky videos. The current video stabilization methods usually take feature trajectories in the background to estimate one global transformation matrix or several…

Volumetric video streaming offers immersive 3D experiences but faces significant challenges due to high bandwidth requirements and latency issues in transmitting detailed content in real time. Traditional methods like point cloud streaming…

Applying image processing algorithms independently to each frame of a video often leads to undesired inconsistent results over time. Developing temporally consistent video-based extensions, however, requires domain knowledge for individual…

Video prediction is a challenging computer vision task that has a wide range of applications. In this work, we present a new family of Transformer-based models for video prediction. Firstly, an efficient local spatial-temporal separation…

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…

Cloud gaming is a multi-billion dollar industry. A client in cloud gaming sends its movement to the game server on the Internet, which renders and transmits the resulting video back. In order to provide a good gaming experience, a latency…

Existing video frame interpolation (VFI) methods blindly predict where each object is at a specific timestep t ("time indexing"), which struggles to predict precise object movements. Given two images of a baseball, there are infinitely many…

A versatile video depth estimation model should (1) be accurate and consistent across frames, (2) produce high-resolution depth maps, and (3) support real-time streaming. We propose FlashDepth, a method that satisfies all three…

Inferring the quality of streaming video applications is important for Internet service providers, but the fact that most video streams are encrypted makes it difficult to do so. We develop models that infer quality metrics (\ie, startup…

We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating at high frame rate, to capture motion at fine temporal…

We propose an end-to-end learned video compression scheme for low-latency scenarios. Previous methods are limited in using the previous one frame as reference. Our method introduces the usage of the previous multiple frames as references.…

Super-resolution (SR) has been widely used to convert low-resolution legacy videos to high-resolution (HR) ones, to suit the increasing resolution of displays (e.g. UHD TVs). However, it becomes easier for humans to notice motion artifacts…

The idea of video super resolution is to use different view points of a single scene to enhance the overall resolution and quality. Classical energy minimization approaches first establish a correspondence of the current frame to all its…

Video frame interpolation (VFI) works generally predict intermediate frame(s) by first estimating the motion between inputs and then warping the inputs to the target time with the estimated motion. This approach, however, is not optimal…

In large-scale applications including medical imaging, collocation differential equation solvers, and estimation with differential privacy, the underlying linear inverse problem can be reformulated as a streaming problem. In theory, the…

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…

This paper introduces a novel dynamic optimization framework for video streaming that leverages Network Digital Twin (NDT) technology to address the challenges posed by fluctuating wireless network conditions. Traditional adaptive streaming…

The ability to predict and therefore to anticipate the future is an important attribute of intelligence. It is also of utmost importance in real-time systems, e.g. in robotics or autonomous driving, which depend on visual scene…