paper-with-me

Papers

Generating time-consistent dynamics with discriminator-guided image diffusion models

2025-05-14 · Philipp Hess, Maximilian Gelbrecht, Christof Schötz, Michael Aich, Yu Huang, Shangshang Yang, Niklas Boers

Realistic temporal dynamics are crucial for many video generation, processing and modelling applications, e.g. in computational fluid dynamics, weather prediction, or long-term climate simulations. Video diffusion models (VDMs) are the current state-of-the-art method for generating highly realistic dynamics. However, training VDMs from scratch can be challenging and requires large computational resources, limiting their wider application. Here, we propose a time-consistency discriminator that enables pretrained image diffusion models to generate realistic spatiotemporal dynamics. The discriminator guides the sampling inference process and does not require extensions or finetuning of the image diffusion model. We compare our approach against a VDM trained from scratch on an idealized turbulence simulation and a real-world global precipitation dataset. Our approach performs equally well in terms of temporal consistency, shows improved uncertainty calibration and lower biases compared to the VDM, and achieves stable centennial-scale climate simulations at daily time steps.

📄 PDF Abstract BibTeX arXiv:2505.09089

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Dynamics Transfer GAN: Generating Video by Transferring Arbitrary Temporal Dynamics from a Source Video to a Single Target Image

2017-12-10 · Wissam J. Baddar, Geonmo Gu, Sangmin Lee, Yong Man Ro

In this paper, we propose Dynamics Transfer GAN; a new method for generating video sequences based on generative adversarial learning. The spatial constructs of a generated video sequence are acquired from the target ima…

Pose Guided Fashion Image Synthesis Using Deep Generative Model

2019-06-17 · Wei Sun, Jawadul H. Bappy, Shanglin Yang, Yi Xu 외

Generating a photorealistic image with intended human pose is a promising yet challenging research topic for many applications such as smart photo editing, movie making, virtual try-on, and fashion display. In this paper…

DecoderImage GenerationPose-Guided Image GenerationVirtual Try-on

SeriesGAN: Time Series Generation via Adversarial and Autoregressive Learning

2024-10-28 · MohammadReza EskandariNasab, Shah Muhammad Hamdi, Soukaina Filali Boubrahimi

Current Generative Adversarial Network (GAN)-based approaches for time series generation face challenges such as suboptimal convergence, information loss in embedding spaces, and instability. To overcome these challenges…

Generative Adversarial NetworkTime SeriesTime Series Generation

Discriminator-Guided Model-Based Offline Imitation Learning

2022-07-01 · Wenjia Zhang, Haoran Xu, Haoyi Niu, Peng Cheng 외

Offline imitation learning (IL) is a powerful method to solve decision-making problems from expert demonstrations without reward labels. Existing offline IL methods suffer from severe performance degeneration under limit…

Decision MakingImitation Learningmodel

Optical-Flow Guided Prompt Optimization for Coherent Video Generation

2024-11-23 · CVPR 2025 1 · Hyelin Nam, JaeMin Kim, Dohun Lee, Jong Chul Ye

While text-to-video diffusion models have made significant strides, many still face challenges in generating videos with temporal consistency. Within diffusion frameworks, guidance techniques have proven effective in enh…

Optical Flow EstimationVideo Generation