DiffRGD: An Inference-Time Diffusion Guidance Through Riemannian Gradient Descent

• URL: http://arxiv.org/abs/2606.28417v2
• Date: Thu, 02 Jul 2026 08:23:41 GMT
• Title: DiffRGD: An Inference-Time Diffusion Guidance Through Riemannian Gradient Descent
• Abstract summary: diffusion models have been widely adopted in generative modeling and have served as foundational models for many image generation tasks.<n>We propose DiffRGD, a distribution-aware guidance framework that explicitly preserves the latent Gaussian structure.
• Score: 19.34344256477806
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, diffusion models have been widely adopted in generative modeling and have served as foundational models for many image generation tasks. To control the generation without costly re-training or fine-tuning, many works seek inference-time guidance methods to steer the latent via a differentiable objective at inference time. However, these methods cannot effectively preserve the original Gaussian distribution because they introduce distributional drift, thereby degrading the sample quality. To address this gap, we propose DiffRGD, a distribution-aware guidance framework that explicitly preserves the latent Gaussian structure. DiffRGD formulates each sampling step as a constrained optimization problem on a spherical manifold induced by the latent Gaussian distribution, and solves it efficiently via Riemannian Gradient Descent (RGD). DiffRGD is a plug-and-play method that can be seamlessly integrated into any pre-trained diffusion model. Extensive experiments demonstrate that DiffRGD outperforms previous methods in most image restoration and conditional generation tasks. Our project page is available at https://diffrgd.github.io/.

Related papers

• Stochastic Transition-Map Distillation for Fast Probabilistic Inference [14.377745343756485]
  Diffusion models achieve strong generation quality, diversity, and distribution coverage, but their performance often comes with expensive inference.<n>In this work, we propose Transition-Map Distillation (STMD), a teacher-free framework for accelerating diffusion model inference.
  arXiv  Detail & Related papers  (2026-05-08T12:31:44Z)
• Test-Time Anchoring for Discrete Diffusion Posterior Sampling [38.507644561076894]
  Posterior sampling is a challenging problem for pretrained discrete diffusion foundation models.<n>We introduce Anchored Posterior Sampling (APS) for masked diffusion foundation models.<n>Our approach achieves state-of-the-art performance among discrete diffusion samplers across linear and nonlinear inverse problems.
  arXiv  Detail & Related papers  (2025-10-02T17:58:37Z)
• Forward-only Diffusion Probabilistic Models [23.247850964456177]
  This work presents a forward-only diffusion (FoD) approach for generative modelling.<n>FoD directly learns data generation through a single forward diffusion process, yielding a simple yet efficient generative framework.<n>Our code is available at https://github.com/Algolzw/FoD.
  arXiv  Detail & Related papers  (2025-05-22T14:47:07Z)
• DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks [79.50756148780928]
  This paper studies the problem of leveraging pretrained diffusion models for performing discriminative tasks.<n>We extend the discriminative capability of pretrained frozen generative diffusion models from the classification task to the more complex object detection task, by "inverting" a pretrained layout-to-image diffusion model.
  arXiv  Detail & Related papers  (2025-04-24T05:13:27Z)
• Constrained Diffusion with Trust Sampling [11.354281911272864]
  We rethink training-free loss-guided diffusion from an optimization perspective. Trust sampling effectively balances following the unconditional diffusion model and adhering to the loss guidance. We demonstrate the efficacy of our method through extensive experiments on complex tasks, and in drastically different domains of images and 3D motion generation.
  arXiv  Detail & Related papers  (2024-11-17T01:34:57Z)
• Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding [84.3224556294803]
  Diffusion models excel at capturing the natural design spaces of images, molecules, DNA, RNA, and protein sequences. We aim to optimize downstream reward functions while preserving the naturalness of these design spaces. Our algorithm integrates soft value functions, which looks ahead to how intermediate noisy states lead to high rewards in the future.
  arXiv  Detail & Related papers  (2024-08-15T16:47:59Z)
• Manifold Preserving Guided Diffusion [121.97907811212123]
  Conditional image generation still faces challenges of cost, generalizability, and the need for task-specific training. We propose Manifold Preserving Guided Diffusion (MPGD), a training-free conditional generation framework.
  arXiv  Detail & Related papers  (2023-11-28T02:08:06Z)
• Gaussian Mixture Solvers for Diffusion Models [84.83349474361204]
  We introduce a novel class of SDE-based solvers called GMS for diffusion models. Our solver outperforms numerous SDE-based solvers in terms of sample quality in image generation and stroke-based synthesis.
  arXiv  Detail & Related papers  (2023-11-02T02:05:38Z)
• Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models [77.83923746319498]
  We propose a framework called Diff-Instruct to instruct the training of arbitrary generative models. We show that Diff-Instruct results in state-of-the-art single-step diffusion-based models. Experiments on refining GAN models show that the Diff-Instruct can consistently improve the pre-trained generators of GAN models.
  arXiv  Detail & Related papers  (2023-05-29T04:22:57Z)
• Hierarchical Integration Diffusion Model for Realistic Image Deblurring [71.76410266003917]
  Diffusion models (DMs) have been introduced in image deblurring and exhibited promising performance. We propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-22T12:18:20Z)
• Towards Controllable Diffusion Models via Reward-Guided Exploration [15.857464051475294]
  We propose a novel framework that guides the training-phase of diffusion models via reinforcement learning (RL) RL enables calculating policy gradients via samples from a pay-off distribution proportional to exponential scaled rewards, rather than from policies themselves. Experiments on 3D shape and molecule generation tasks show significant improvements over existing conditional diffusion models.
  arXiv  Detail & Related papers  (2023-04-14T13:51:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.