Diffusion Models for Video Prediction and Infilling
read the original abstract
Predicting and anticipating future outcomes or reasoning about missing information in a sequence are critical skills for agents to be able to make intelligent decisions. This requires strong, temporally coherent generative capabilities. Diffusion models have shown remarkable success in several generative tasks, but have not been extensively explored in the video domain. We present Random-Mask Video Diffusion (RaMViD), which extends image diffusion models to videos using 3D convolutions, and introduces a new conditioning technique during training. By varying the mask we condition on, the model is able to perform video prediction, infilling, and upsampling. Due to our simple conditioning scheme, we can utilize the same architecture as used for unconditional training, which allows us to train the model in a conditional and unconditional fashion at the same time. We evaluate RaMViD on two benchmark datasets for video prediction, on which we achieve state-of-the-art results, and one for video generation. High-resolution videos are provided at https://sites.google.com/view/video-diffusion-prediction.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
A new shared video-image tokenizer enables large language models to surpass diffusion models on standard visual generation benchmarks.
-
Phenaki: Variable Length Video Generation From Open Domain Textual Description
Phenaki generates arbitrary-length videos from sequences of text prompts by tokenizing videos with causal temporal attention and generating tokens with a text-conditioned masked transformer, trained jointly on images ...
-
ELT: Elastic Looped Transformers for Visual Generation
Elastic Looped Transformers share weights across recurrent blocks and apply intra-loop self-distillation to deliver 4x parameter reduction while matching competitive FID and FVD scores on ImageNet and UCF-101.
-
Frozen Forecasting: A Unified Evaluation
A new evaluation framework using latent diffusion on frozen vision backbones shows video-pretrained models consistently outperform image-based ones in forecasting entire trajectories across abstraction levels.
-
Long-Context Autoregressive Video Modeling with Next-Frame Prediction
FAR baseline plus asymmetric kernels for long short-term context modeling achieves SOTA short and long video generation in autoregressive setups.
-
Probabilistic Precipitation Nowcasting with Rectified Flow Transformers
FREUD applies rectified flow transformers with frame-wise encoding and a unified decoder to achieve state-of-the-art probabilistic precipitation nowcasting on the SEVIR benchmark.
-
I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models
I2VGen-XL applies cascaded diffusion models with a base stage for semantic preservation via hierarchical encoders and a refinement stage for detail and resolution, trained on 35 million text-video and 6 billion text-i...
-
ModelScope Text-to-Video Technical Report
ModelScopeT2V is a 1.7-billion-parameter text-to-video model built on Stable Diffusion that adds temporal modeling and outperforms prior methods on three evaluation metrics.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.