paper-with-me

Papers

Topology Guidance: Controlling the Outputs of Generative Models via Vector Field Topology

2025-05-11 · Xiaohan Wang, Matthew Berger

For domains that involve numerical simulation, it can be computationally expensive to run an ensemble of simulations spanning a parameter space of interest to a user. To this end, an attractive surrogate for simulation is the generative modeling of fields produced by an ensemble, allowing one to synthesize fields in a computationally cheap, yet accurate, manner. However, for the purposes of visual analysis, a limitation of generative models is their lack of control, as it is unclear what one should expect when sampling a field from a model. In this paper we study how to make generative models of fields more controllable, so that users can specify features of interest, in particular topological features, that they wish to see in the output. We propose topology guidance, a method for guiding the sampling process of a generative model, specifically a diffusion model, such that a topological description specified as input is satisfied in the generated output. Central to our method, we couple a coordinate-based neural network used to represent fields, with a diffusion model used for generation. We show how to use topologically-relevant signals provided by the coordinate-based network to help guide the denoising process of a diffusion model. This enables us to faithfully represent a user's specified topology, while ensuring that the output field remains within the generative data distribution. Specifically, we study 2D vector field topology, evaluating our method over an ensemble of fluid flows, where we show that generated vector fields faithfully adhere to the location, and type, of critical points over the spatial domain. We further show the benefits of our method in aiding the comparison of ensembles, allowing one to explore commonalities and differences in distributions along prescribed topological features.

📄 PDF Abstract BibTeX arXiv:2505.06804

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

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

Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance

2025-08-28 · Luozhijie Jin, Zijie Qiu, Jie Liu, Zijie Diao 외 arxiv

Denoising-based generative models, particularly diffusion and flow matching algorithms, have achieved remarkable success. However, aligning their output distributions with complex downstream objectives, such as human pre…

Reinforcement Learning

Low-Resource Guidance for Controllable Latent Audio Diffusion

2026-03-04 · Zachary Novack, Zack Zukowski, CJ Carr, Julian Parker 외 arxiv

Generative audio requires fine-grained controllable outputs, yet most existing methods require model retraining on specific controls or inference-time controls (\textit{e.g.}, guidance) that can also be computationally d…

FlowGrad: Controlling the Output of Generative ODEs With Gradients

2023-01-01 · CVPR 2023 1 · Xingchao Liu, Lemeng Wu, Shujian Zhang, Chengyue Gong 외

Generative modeling with ordinary differential equations (ODEs) has achieved fantastic results on a variety of applications. Yet, few works have focused on controlling the generated content of a pre-trained ODE-based…

Image Manipulation

CREPE: Controlling Diffusion with Replica Exchange

2025-09-27 · Jiajun He, Paul Jeha, Peter Potaptchik, Leo Zhang 외 arxiv

Inference-time control of diffusion models aims to steer model outputs to satisfy new constraints without retraining. Previous approaches have mostly relied on heuristic guidance or have been coupled with Sequential Mont…

Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models

2026-05-29 · Shreyansh Modi, Akshat Tomar, Aarush Aggarwal arxiv

Unconditional diffusion models offer powerful generative priors, yet steering them toward aesthetically enhanced outputs remains largely unexplored. We show that h-space patching, the dominant paradigm for training-free …