paper-with-me

Papers

Generative Image Dynamics

2023-09-14 · CVPR 2024 1 · Zhengqi Li, Richard Tucker, Noah Snavely, Aleksander Holynski

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 depicting natural, oscillatory dynamics such as trees, flowers, candles, and clothes swaying in the wind. We model this dense, long-term motion prior in the Fourier domain:given a single image, our trained model uses a frequency-coordinated diffusion sampling process to predict a spectral volume, which can be converted into a motion texture that spans an entire video. Along with an image-based rendering module, these trajectories can be used for a number of downstream applications, such as turning still images into seamlessly looping videos, or allowing users to realistically interact with objects in real pictures by interpreting the spectral volumes as image-space modal bases, which approximate object dynamics.

📄 PDF Abstract BibTeX arXiv:2309.07906

Code (1)

fltwr/generative-image-dynamics pytorch

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

Concept Formation and Dynamics of Repeated Inference in Deep Generative Models

2017-12-12 · Yoshihiro Nagano, Ryo Karakida, Masato Okada

Deep generative models are reported to be useful in broad applications including image generation. Repeated inference between data space and latent space in these models can denoise cluttered images and improve the quali…

Image Generation

Spontaneous Symmetry Breaking in Generative Diffusion Models

2023-05-31 · NeurIPS 2023 11 · Gabriel Raya, Luca Ambrogioni

Generative diffusion models have recently emerged as a leading approach for generating high-dimensional data. In this paper, we show that the dynamics of these models exhibit a spontaneous symmetry breaking that divides …

Diversity

WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions

2025-05-23 · Zizhang Li, Hong-Xing Yu, Wei Liu, Yin Yang 외

WonderPlay is a novel framework integrating physics simulation with video generation for generating action-conditioned dynamic 3D scenes from a single image. While prior works are restricted to rigid body or simple elast…

SandScene GenerationVideo Generation

Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory

2025-10-14 · Hanru Bai, Weiyang Ding, Difan Zou arxiv

Diffusion models have achieved impressive success in high-fidelity image generation but suffer from slow sampling due to their inherently iterative denoising process. While recent one-step methods accelerate inference by…

Image Generation

Posterior sampling via Langevin dynamics based on generative priors

2024-10-02 · Vishal Purohit, Matthew Repasky, Jianfeng Lu, Qiang Qiu 외

Posterior sampling in high-dimensional spaces using generative models holds significant promise for various applications, including but not limited to inverse problems and guided generation tasks. Despite many recent dev…

Image Restoration