State of the" art”: A taxonomy of artistic stylization techniques for images and video

JE Kyprianidis, J Collomosse, T Wang… - IEEE transactions on …, 2012 - ieeexplore.ieee.org
This paper surveys the field of nonphotorealistic rendering (NPR), focusing on techniques
for transforming 2D input (images and video) into artistically stylized renderings. We first …

State of the art in example-based texture synthesis

LY Wei, S Lefebvre, V Kwatra, G Turk - … 2009, State of the Art Report …, 2009 - inria.hal.science
Recent years have witnessed significant progress in example-based texture synthesis
algorithms. Given an example texture, these methods produce a larger texture that is tailored …

Sequential modeling enables scalable learning for large vision models

Y Bai, X Geng, K Mangalam, A Bar… - Proceedings of the …, 2024 - openaccess.thecvf.com
We introduce a novel sequential modeling approach which enables learning a Large Vision
Model (LVM) without making use of any linguistic data. To do this we define a common …

Generative image dynamics

Z Li, R Tucker, N Snavely… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
We present an approach to modeling an image-space prior on scene motion. Our prior is
learned from a collection of motion trajectories extracted from real video sequences …

Generating long videos of dynamic scenes

T Brooks, J Hellsten, M Aittala… - Advances in …, 2022 - proceedings.neurips.cc
We present a video generation model that accurately reproduces object motion, changes in
camera viewpoint, and new content that arises over time. Existing video generation methods …

Video-to-video synthesis

TC Wang, MY Liu, JY Zhu, G Liu, A Tao, J Kautz… - arXiv preprint arXiv …, 2018 - arxiv.org
We study the problem of video-to-video synthesis, whose goal is to learn a mapping function
from an input source video (eg, a sequence of semantic segmentation masks) to an output …

Physgen: Rigid-body physics-grounded image-to-video generation

S Liu, Z Ren, S Gupta, S Wang - European Conference on Computer …, 2024 - Springer
We present PhysGen, a novel image-to-video generation method that converts a single
image and an input condition (eg., force and torque applied to an object in the image) to …

Visual dynamics: Probabilistic future frame synthesis via cross convolutional networks

T Xue, J Wu, K Bouman… - Advances in neural …, 2016 - proceedings.neurips.cc
We study the problem of synthesizing a number of likely future frames from a single input
image. In contrast to traditional methods, which have tackled this problem in a deterministic …

Infinite nature: Perpetual view generation of natural scenes from a single image

A Liu, R Tucker, V Jampani… - Proceedings of the …, 2021 - openaccess.thecvf.com
We introduce the problem of perpetual view generation-long-range generation of novel
views corresponding to an arbitrarily long camera trajectory given a single image. This is a …

Learning stable deep dynamics models

JZ Kolter, G Manek - Advances in neural information …, 2019 - proceedings.neurips.cc
Deep networks are commonly used to model dynamical systems, predicting how the state of
a system will evolve over time (either autonomously or in response to control inputs) …