Video generation necessitates both global coherence and local realism. This work presents
a novel non-autoregressive method GLOBER, which first generates global features to obtain …

Video prediction, a fundamental task in computer vision, aims to enable models to generate
sequences of future frames based on existing video content. This task has garnered …

For autoregressive image generation, vector-quantized VAEs (VQ-VAEs) quantize image
features with discrete codebook entries and reconstruct images from quantized features …

Predicting future frames of a video is challenging because it is difficult to learn the
uncertainty of the underlying factors influencing their contents. In this paper, we propose a …

Satellite image sequence prediction aims to precisely infer future satellite image frames with
historical observations, which is a significant and challenging dense prediction task. Though …

Text-driven Image to Video Generation (TI2V) aims to generate controllable video given the
first frame and corresponding textual description. The primary challenges of this task lie in …

We introduce motion graph, a novel approach to the video prediction problem, which
predicts future video frames from limited past data. The motion graph transforms patches of …

The prediction task is significantly challenged by the intricate scene information and motion
variations present in spatiotemporal data. Existing prediction methods struggle to accurately …

Visual deep learning (VDL) systems have shown significant success in real-world
applications like image recognition, object detection, and autonomous driving. To evaluate …

Since videos record objects moving coherently, adjacent video frames have commonness
(similar object appearances) and uniqueness (slightly changed postures). To prevent …