Anisotropic Diffusion Stencils: From Simple Derivations over Stability Estimates to ResNet Implementations

• URL: http://arxiv.org/abs/2309.05575v3
• Date: Mon, 8 Apr 2024 15:26:25 GMT
• Title: Anisotropic Diffusion Stencils: From Simple Derivations over Stability Estimates to ResNet Implementations
• Authors: Karl Schrader, Joachim Weickert, Michael Krause,
• Abstract summary: We study a large family of finite difference discretisations on a 3 x 3 stencil. We derive it by splitting 2-D anisotropic diffusion into four 1-D diffusions. We establish a bound on the spectral norm of the matrix corresponding to the stencil.
• Score: 6.923007095578702
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Anisotropic diffusion processes with a diffusion tensor are important in image analysis, physics, and engineering. However, their numerical approximation has a strong impact on dissipative artefacts and deviations from rotation invariance. In this work, we study a large family of finite difference discretisations on a 3 x 3 stencil. We derive it by splitting 2-D anisotropic diffusion into four 1-D diffusions. The resulting stencil class involves one free parameter and covers a wide range of existing discretisations. It comprises the full stencil family of Weickert et al. (2013) and shows that their two parameters contain redundancy. Furthermore, we establish a bound on the spectral norm of the matrix corresponding to the stencil. This gives time step size limits that guarantee stability of an explicit scheme in the Euclidean norm. Our directional splitting also allows a very natural translation of the explicit scheme into ResNet blocks. Employing neural network libraries enables simple and highly efficient parallel implementations on GPUs.

Related papers

• 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)
• Intention-aware Denoising Diffusion Model for Trajectory Prediction [14.524496560759555]
  Trajectory prediction is an essential component in autonomous driving, particularly for collision avoidance systems. We propose utilizing the diffusion model to generate the distribution of future trajectories. We propose an Intention-aware denoising Diffusion Model (IDM) Our methods achieve state-of-the-art results, with an FDE of 13.83 pixels on the SDD dataset and 0.36 meters on the ETH/UCY dataset.
  arXiv  Detail & Related papers  (2024-03-14T09:05:25Z)
• Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models [82.8261101680427]
  Smooth latent spaces ensure that a perturbation on an input latent corresponds to a steady change in the output image. This property proves beneficial in downstream tasks, including image inversion, inversion, and editing. We propose Smooth Diffusion, a new category of diffusion models that can be simultaneously high-performing and smooth.
  arXiv  Detail & Related papers  (2023-12-07T16:26:23Z)
• Eliminating Lipschitz Singularities in Diffusion Models [51.806899946775076]
  We show that diffusion models frequently exhibit the infinite Lipschitz near the zero point of timesteps. This poses a threat to the stability and accuracy of the diffusion process, which relies on integral operations. We propose a novel approach, dubbed E-TSDM, which eliminates the Lipschitz of the diffusion model near zero.
  arXiv  Detail & Related papers  (2023-06-20T03:05:28Z)
• SinDiffusion: Learning a Diffusion Model from a Single Natural Image [159.4285444680301]
  We present SinDiffusion, leveraging denoising diffusion models to capture internal distribution of patches from a single natural image. It is based on two core designs. First, SinDiffusion is trained with a single model at a single scale instead of multiple models with progressive growing of scales. Second, we identify that a patch-level receptive field of the diffusion network is crucial and effective for capturing the image's patch statistics.
  arXiv  Detail & Related papers  (2022-11-22T18:00:03Z)
• The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization [13.872374586700767]
  Recent work has shown that shaping the activation function as network depth grows large is necessary. We identify the precise scaling of the activation function necessary to arrive at a nontrivial limit. We recover an if-and-only-if condition for exploding and vanishing norms of large shaped networks based on the activation function.
  arXiv  Detail & Related papers  (2022-06-06T17:45:07Z)
• Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation [64.92152574895111]
  We propose a simple Orthogonal Jacobian Regularization (OroJaR) to encourage deep generative model to learn disentangled representations. Our method is effective in disentangled and controllable image generation, and performs favorably against the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-08-17T15:01:46Z)
• Manifold-aware Synthesis of High-resolution Diffusion from Structural Imaging [12.96280888284293]
  We propose a network architecture for the direct generation of diffusion tensors (DT) and diffusion orientation distribution functions (dODFs) from high-resolution T1w images. Our approach improves the fractional anisotropy mean squared error (FA MSE) between the synthesized diffusion and the ground-truth by more than 23%. While our method is able to generate high-resolution diffusion images from structural inputs in less than 15 seconds, we acknowledge and discuss the limits of diffusion inference solely relying on T1w images.
  arXiv  Detail & Related papers  (2021-08-09T16:00:40Z)
• Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields [53.31927549039624]
  We show that a piecewise discretization preserves better contrast from existing discretization problems. We apply this theory to the problem of matching two images.
  arXiv  Detail & Related papers  (2021-07-13T12:31:06Z)
• Manifold-Aware CycleGAN for High-Resolution Structural-to-DTI Synthesis [8.829738147738222]
  We propose a manifold-aware CycleGAN that learns the generation of high-resolution DTI from unpaired T1w images. Our method is able to generate realistic high-resolution DTI that can be used to compute diffusion-based metrics and potentially run fiber tractography algorithms.
  arXiv  Detail & Related papers  (2020-04-01T00:08:14Z)

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.