Related papers: Self-Refining Video Sampling
Video summarization is a crucial research area that aims to efficiently browse and retrieve relevant information from the vast amount of video content available today. With the exponential growth of multimedia data, the ability to extract…
We offer a new perspective on approaching the task of video generation. Instead of directly synthesizing a sequence of frames, we propose to render a video by warping one static image with a generative deformation field (GenDeF). Such a…
Video Generation is a relatively new and yet popular subject in machine learning due to its vast variety of potential applications and its numerous challenges. Current methods in Video Generation provide the user with little or no control…
Recently, Neural Radiance Fields (NeRF) have emerged as a potent method for synthesizing novel views from a dense set of images. Despite its impressive performance, NeRF is plagued by its necessity for numerous calibrated views and its…
We propose a method for generating a temporally remapped video that matches the desired target duration while maximally preserving natural video dynamics. Our approach trains a neural network through self-supervision to recognize and…
Deep learning is now the gold standard in computer vision-based quality inspection systems. In order to detect defects, supervised learning is often utilized, but necessitates a large amount of annotated images, which can be costly:…
In this work, we rethink the approach to video super-resolution by introducing a method based on the Diffusion Posterior Sampling framework, combined with an unconditional video diffusion transformer operating in latent space. The video…
We address an essential problem in computer vision, that of unsupervised object segmentation in video, where a main object of interest in a video sequence should be automatically separated from its background. An efficient solution to this…
Machine learning techniques work best when the data used for training resembles the data used for evaluation. This holds true for learned single-image denoising algorithms, which are applied to real raw camera sensor readings but, due to…
Videos show continuous events, yet most $-$ if not all $-$ video synthesis frameworks treat them discretely in time. In this work, we think of videos of what they should be $-$ time-continuous signals, and extend the paradigm of neural…
Observable motion in videos can give rise to the definition of objects moving with respect to the scene. The task of segmenting such moving objects is referred to as motion segmentation and is usually tackled either by aggregating motion…
Existing video deraining methods are often trained on paired datasets, either synthetic, which limits their ability to generalize to real-world rain, or captured by static cameras, which restricts their effectiveness in dynamic scenes with…
Semantic segmentation labels are expensive and time consuming to acquire. Hence, pretraining is commonly used to improve the label-efficiency of segmentation models. Typically, the encoder of a segmentation model is pretrained as a…
In this paper we present a a deep generative model for lossy video compression. We employ a model that consists of a 3D autoencoder with a discrete latent space and an autoregressive prior used for entropy coding. Both autoencoder and prior…
Video inpainting tasks have seen significant improvements in recent years with the rise of deep neural networks and, in particular, vision transformers. Although these models show promising reconstruction quality and temporal consistency,…
For many of the physical phenomena around us, we have developed sophisticated models explaining their behavior. Nevertheless, inferring specifics from visual observations is challenging due to the high number of causally underlying physical…
Recent diffusion-based video generation models can synthesize visually plausible videos, yet they often struggle to satisfy physical constraints. A key reason is that most existing approaches remain single-stage: they entangle high-level…
Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumulation and long inference times. In this work, we propose a…
In the past few years, machine learning-based approaches have had some great success for rendering animated feature films. This survey summarizes several of the most dramatic improvements in using deep neural networks over traditional…
Diffusion models have revolutionized image and video generation, achieving unprecedented visual quality. However, their reliance on transformer architectures incurs prohibitively high computational costs, particularly when extending…