Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

computer-vision-9

Unconditional Video Generation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in unconditional-video-generation-9

Trend

Dataset

Best Model

Actions

CelebV-HQ

Libraries

Use these libraries to find unconditional-video-generation-9 models and implementations

Datasets

CelebV-HQ

Subtasks

No subtasks available.

Most implemented papers

MOSO: Decomposing MOtion, Scene and Object for Video Prediction

Mingzhe Sun, Weining Wang, Xinxin Zhu, Jing Liu•Mon Mar 06 2023

A two-stage MOtion, Scene and Object decomposition framework (MOSO) that achieves new state-of-the-art performance on five challenging benchmarks for video prediction and unconditional video generation and can be easily extended to unconditionalVideo generation and video frame interpolation tasks.

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Latent Neural Differential Equations for Video Generation

Cade Gordon, Natalie Parde•Fri Nov 06 2020

This work proposes studying the effects of Neural Differential Equations to model the temporal dynamics of video generation, and investigates how changes in temporal models affect generated video quality.

12 0

Paper Graph

CelebV-HQ: A Large-Scale Video Facial Attributes Dataset

Ziwei Liu, Chen Change Loy, Wayne Wu, Liming Jiang, Haoning Zhu, Wentao Zhu, Siwei Tang, Li Zhang•Sun Jul 24 2022

This work proposes a large-scale, high-quality, and diverse video dataset with rich facial attribute annotations, named the High-Quality Celebrity Video Dataset (CelebV-HQ), and conducts a comprehensive analysis in terms of age, ethnicity, brightness stability, motion smoothness, head pose diversity, and data quality.

260 0

Paper Graph

MotionVideoGAN: A Novel Video Generator Based on the Motion Space Learned From Image Pairs

Jin Zhu, Huimin Ma, Jiansheng Chen, Jian Yuan•Sun Mar 05 2023

This work designs a novel framework to build the motion space, aiming to achieve content consistency and fast convergence for video generation, and proposes an image pair generator named MotionStyleGAN to generate image pairs sharing the same contents and producing various motions.

7 0

Paper Graph

Video Diffusion Models with Local-Global Context Guidance

Si-hang Yang, Lu Zhang, Yu Liu, Zhizhuo Jiang, You He•Sun Jun 04 2023

A local-global context guidance strategy to capture the multi-perceptual embedding of the past fragment to boost the consistency of future prediction and a two-stage training strategy to alleviate the effect of noisy frames for more stable predictions.

18 0

Paper Graph

DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles

Aviv Tamar, Tal Daniel•Thu Jun 08 2023

The interpretable nature of DDLP allows us to perform ``what-if'' generation -- predict the consequence of changing properties of objects in the initial frames, and DLP's compact structure enables efficient diffusion-based unconditional video generation.

16 0

Paper Graph

StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generation

Chen Change Loy, Liming Jiang, Yuhan Wang•Wed Aug 30 2023

A novel motion generator design that uses a learning-based inversion network for GAN and enjoys the advantage of sparse training and naturally constrains the generation space of the motion generator with the inversion network guided by the initial frame, eliminating the need for heavy discriminators.

18 0

Paper Graph

StyleCineGAN: Landscape Cinemagraph Generation Using a Pre-trained StyleGAN

Kwanggyoon Seo, Amirsaman Ashtari, Jun-yong Noh, Jongwoo Choi•Wed Mar 20 2024

This work proposes multi-scale deep feature warping (MSDFW), which warps the intermediate features of a pre-trained StyleGAN at different resolutions, and generates cinemagraphs automatically from a still landscape image using a pre-trained StyleGAN.

5 0

Paper Graph

Adding a benchmark result helps the community track progress.

Unconditional Video Generation | State-of-the-Art