Video Diffusion Models
07 Apr 2022
TL;DR: The authors proposed a diffusion model for video generation, which is a natural extension of the standard image diffusion architecture and enables jointly training from image and video data, which they find to reduce the variance of minibatch gradients and speed up optimization.
read more
Abstract: Generating temporally coherent high fidelity video is an important milestone in generative modeling research. We make progress towards this milestone by proposing a diffusion model for video generation that shows very promising initial results. Our model is a natural extension of the standard image diffusion architecture, and it enables jointly training from image and video data, which we find to reduce the variance of minibatch gradients and speed up optimization. To generate long and higher resolution videos we introduce a new conditional sampling technique for spatial and temporal video extension that performs better than previously proposed methods. We present the first results on a large text-conditioned video generation task, as well as state-of-the-art results on established benchmarks for video prediction and unconditional video generation. Supplementary material is available at https://video-diffusion.github.io/
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Diffusion Models in Vision: A Survey
TL;DR: Denoising diffusion models represent a recent emerging topic in computer vision, demonstrating remarkable results in the area of generative modeling as discussed by the authors , and are widely appreciated for the quality and diversity of the generated samples, despite their known computational burdens.
Diffusion Models: A Comprehensive Survey of Methods and Applications
Lu Yang,Zhilong Zhang,Yang Song,Shenda Hong,Runsheng Xu,Yang Zhao,Wentao Zhang,Bin Cui,Ming–Hsuan Yang +8 more
TL;DR: Diffusion models are a powerful family of generative models for image, video, and molecule generation with record-breaking performance. This survey categorizes the research into sampling, likelihood estimation, and data handling with special structures. It also discusses potential combinations with other generative models and applications in various fields.
478
InstructPix2Pix: Learning to Follow Image Editing Instructions
Tim Brooks,Aleksander Holynski,Alexei A. Efros +2 more
- 01 Jun 2023
TL;DR: InstructPix2Pix learns to edit images from human instructions by generating a large dataset of image editing examples and training a conditional diffusion model on it.
458
Align Your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
Andreas Blattmann,Robin Rombach,Huan Ling,Tim Dockhorn,Seung Wook Kim,Sanja Fidler,Karsten Kreis +6 more
- 01 Jun 2023
TL;DR: High-resolution video synthesis with latent diffusion models enables high-quality video generation while reducing compute demands.
226
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
Jay Zhangjie Wu,Yixiao Ge,Xintao Wang,Stan Weixian Lei,Yuchao Gu,Yufei Shi,Wynne Hsu,Ying Shi,Xiaohu Qie,Mike Zheng Shou +9 more
- 01 Oct 2023
TL;DR: Tune-A-Video enables one-shot tuning of image diffusion models for T2V generation, leveraging pre-trained T2I models and introducing a tailored spatio-temporal attention mechanism.
176
References
PixelSNAIL: an Improved Autoregressive Generative Model.
Xi Chen,Nikhil Mishra,Mostafa Rohaninejad,Pieter Abbeel +3 more
TL;DR: Researchers introduce PixelSNAIL, an improved autoregressive generative model combining causal convolutions with self-attention, achieving state-of-the-art log-likelihood results on CIFAR-10 and ImageNet, outperforming previous models with 2.85 and 3.80 bits per dim, respectively.
Adversarial Video Generation on Complex Datasets
Aidan Clark,Jeff Donahue,Karen Simonyan +2 more
TL;DR: This study presents a large-scale Generative Adversarial Network (GAN) model, DVD-GAN, that generates high-fidelity video samples on complex datasets, achieving state-of-the-art results in video synthesis and prediction tasks, particularly on Kinetics-600 and UCF-101 datasets.
Latent Neural Differential Equations for Video Generation
Cade Gordon,Natalie Parde +1 more
TL;DR: This study introduces Latent Neural Differential Equations for video generation, leveraging their continuous time representation to improve quality and efficiency, achieving a new state-of-the-art Inception Score of 15.20 in 64x64 pixel unconditional video generation.
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models.
Alex Nichol,Prafulla Dhariwal,Aditya Ramesh,Pranav Shyam,Pamela Mishkin,Bob McGrew,Ilya Sutskever,Mark Chen +7 more
TL;DR: Researchers develop GLIDE, a text-guided diffusion model for photorealistic image generation and editing, outperforming DALL-E in human evaluations and demonstrating fine-tuning capabilities for image inpainting and text-driven editing.
UCF101: A Dataset of 101 Human Actions Classes from Videos in the Wild
Khurram Soomro,Amir Roshan Zamir,Mubarak Shah +2 more
TL;DR: UCF101 is a large-scale human action dataset with 101 classes, 13k clips, and 27 hours of video data, featuring realistic user-uploaded videos with camera motion and cluttered backgrounds, posing a challenging task for action recognition.
Related Papers (5)
Chi-Farn Chen,Min-Hsin Chen +1 more
- 10 Dec 2006
Kamlesh Vrma,Debashis Ghosh,Avnish Kumar +2 more
- 01 Nov 2018