Objects as volumes: A stochastic geometry view of opaque solids

• URL: http://arxiv.org/abs/2312.15406v2
• Date: Tue, 16 Apr 2024 06:33:09 GMT
• Title: Objects as volumes: A stochastic geometry view of opaque solids
• Authors: Bailey Miller, Hanyu Chen, Alice Lai, Ioannis Gkioulekas,
• Abstract summary: We develop a theory for the representation of opaque solids as volumes. We prove the conditions under which such solids can be modeled using exponential volumetric transport. We propose meaningful extensions that lead to improved performance in 3D reconstruction tasks.
• Score: 11.776706744304613
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We develop a theory for the representation of opaque solids as volumes. Starting from a stochastic representation of opaque solids as random indicator functions, we prove the conditions under which such solids can be modeled using exponential volumetric transport. We also derive expressions for the volumetric attenuation coefficient as a functional of the probability distributions of the underlying indicator functions. We generalize our theory to account for isotropic and anisotropic scattering at different parts of the solid, and for representations of opaque solids as stochastic implicit surfaces. We derive our volumetric representation from first principles, which ensures that it satisfies physical constraints such as reciprocity and reversibility. We use our theory to explain, compare, and correct previous volumetric representations, as well as propose meaningful extensions that lead to improved performance in 3D reconstruction tasks.

Related papers

• Supervised Guidance Training for Infinite-Dimensional Diffusion Models [47.65586147952857]
  In inverse problems, the aim is to sample from a posterior distribution over functions obtained by conditioning a prior.<n>We prove that the models can be conditioned using an infinite-dimensional extension of Doob's $h$-transform.<n>We propose a simulation-free score matching objective (called Supervised Guidance Training) enabling efficient and stable posterior sampling.
  arXiv  Detail & Related papers  (2026-01-28T16:39:39Z)
• Density of scattering resonances in a disordered system [0.0]
  We develop a general approach to study the distribution function of resonance widths based on the nonlinear sigma model.<n>We derive an integral representation of the distribution function that works equally well for systems of any symmetry and for any type of coupling to the measuring device.
  arXiv  Detail & Related papers  (2025-12-21T12:30:39Z)
• A Free Probabilistic Framework for Denoising Diffusion Models: Entropy, Transport, and Reverse Processes [22.56299060022639]
  This paper builds on Voiculescu's theory of free entropy and free Fisher information.<n>We formulate diffusion and quantify reverse processes governed by operator-valued dynamics.<n>The resulting dynamics admit a gradient-flow structure in the noncommutative Wasserstein space.
  arXiv  Detail & Related papers  (2025-10-26T18:03:54Z)
• Emergence of Quantised Representations Isolated to Anisotropic Functions [0.0]
  This paper builds upon the existing Spotlight Resonance method to determine representational alignment.<n>A new tool is used to gain insight into how discrete representations can emerge and organise in autoencoder models.
  arXiv  Detail & Related papers  (2025-07-16T09:27:54Z)
• Can Diffusion Models Disentangle? A Theoretical Perspective [52.360881354319986]
  This paper presents a novel theoretical framework for understanding how diffusion models can learn disentangled representations. We establish identifiability conditions for general disentangled latent variable models, analyze training dynamics, and derive sample complexity bounds for disentangled latent subspace models.
  arXiv  Detail & Related papers  (2025-03-31T20:46:18Z)
• Counterfactual Realizability [52.85109506684737]
  We introduce a formal definition of realizability, the ability to draw samples from a distribution, and then develop a complete algorithm to determine whether an arbitrary counterfactual distribution is realizable. We illustrate the implications of this new framework for counterfactual data collection using motivating examples from causal fairness and causal reinforcement learning.
  arXiv  Detail & Related papers  (2025-03-14T20:54:27Z)
• Physical consequences of Lindbladian invariance transformations [44.99833362998488]
  We show that symmetry transformations can be exploited, on their own, to optimize practical physical tasks. In particular, we show how they can be used to change the measurable values of physical quantities regarding the exchange of energy and/or information with the environment.
  arXiv  Detail & Related papers  (2024-07-02T18:22:11Z)
• Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models [59.331993845831946]
  Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. This paper provides the first theoretical study towards understanding the influence of guidance on diffusion models in the context of Gaussian mixture models.
  arXiv  Detail & Related papers  (2024-03-03T23:15:48Z)
• Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies [58.179981892921056]
  This work introduces a novel principle for disentanglement we call mechanism sparsity regularization. We propose a representation learning method that induces disentanglement by simultaneously learning the latent factors. We show that the latent factors can be recovered by regularizing the learned causal graph to be sparse.
  arXiv  Detail & Related papers  (2024-01-10T02:38:21Z)
• Algebras of actions in an agent's representations of the world [51.06229789727133]
  We use our framework to reproduce the symmetry-based representations from the symmetry-based disentangled representation learning formalism. We then study the algebras of the transformations of worlds with features that occur in simple reinforcement learning scenarios. Using computational methods, that we developed, we extract the algebras of the transformations of these worlds and classify them according to their properties.
  arXiv  Detail & Related papers  (2023-10-02T18:24:51Z)
• Covariant operator bases for continuous variables [0.0]
  We work out an alternative basis consisting of monomials on the basic observables, with the crucial property of behaving well under symplectic transformations. Given the density matrix of a state, the expansion coefficients in that basis constitute the multipoles, which describe the state in a canonically covariant form that is both concise and explicit.
  arXiv  Detail & Related papers  (2023-09-18T18:00:15Z)
• Inelastic decay from integrability [0.0]
  We show that inelastic decay can be observed in circuit QED realizations of integrable boundary models. We consider the scattering of microwave photons off impurities in superconducting circuits implementing the boundary sine-Gordon and Kondo models.
  arXiv  Detail & Related papers  (2023-08-29T18:02:13Z)
• The kinetic Hamiltonian with position-dependent mass [0.0]
  We examine in a systematic way the most relevant orderings of pure kinetic Hamiltonians for five different position-dependent mass profiles. As a result of the non-commutativity between momentum and position operators, a diversity of effective potentials is generated. We obtain analytically the full-spectrum of energies and solutions in the twenty-five cases considered.
  arXiv  Detail & Related papers  (2023-03-04T21:23:42Z)
• Third quantization of open quantum systems: new dissipative symmetries and connections to phase-space and Keldysh field theory formulations [77.34726150561087]
  We reformulate the technique of third quantization in a way that explicitly connects all three methods. We first show that our formulation reveals a fundamental dissipative symmetry present in all quadratic bosonic or fermionic Lindbladians. For bosons, we then show that the Wigner function and the characteristic function can be thought of as ''wavefunctions'' of the density matrix.
  arXiv  Detail & Related papers  (2023-02-27T18:56:40Z)
• Fundamental transfer matrix and dynamical formulation of stationary scattering in two and three dimensions [0.0]
  We offer a consistent dynamical formulation of stationary scattering in two and three dimensions. We show that a proper formulation of this approach requires the introduction of a pair of intertwined transfer matrices each related to the time-evolution operator. We discuss the utility of our approach in characterizing invisible (scattering-free) potentials and potentials.
  arXiv  Detail & Related papers  (2021-09-14T08:50:31Z)
• Learning Disentangled Representations with Latent Variation Predictability [102.4163768995288]
  This paper defines the variation predictability of latent disentangled representations. Within an adversarial generation process, we encourage variation predictability by maximizing the mutual information between latent variations and corresponding image pairs. We develop an evaluation metric that does not rely on the ground-truth generative factors to measure the disentanglement of latent representations.
  arXiv  Detail & Related papers  (2020-07-25T08:54:26Z)

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.