SDDBMs: Soft Denoising Diffusion Bridge Models

• URL: http://arxiv.org/abs/2608.08594v2
• Date: Tue, 11 Aug 2026 14:57:08 GMT
• Title: SDDBMs: Soft Denoising Diffusion Bridge Models
• Abstract summary: Diffusion bridge models leverage Doob's (h)-transform to construct transports between arbitrary endpoint distributions.<n>Most existing bridge models rely on hard endpoint conditioning, which forces the terminal state to match a prescribed target exactly.<n>We propose Soft Denoising Diffusion Bridge Models (SDDBMs), a framework that regularizes diffusion bridges directly at the level of their terminal constraints.
• Score: 9.271715699156374
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion bridge models leverage Doob's \(h\)-transform to construct stochastic transports between arbitrary endpoint distributions, and have shown strong potential in image-to-image translation and restoration. However, most existing bridge models rely on hard endpoint conditioning, which forces the terminal state to match a prescribed target exactly. This hard constraint induces terminal-boundary singularities: the terminal law collapses to a Dirac measure, and the resulting drift coefficients become ill-conditioned near the endpoint. In this paper, we propose Soft Denoising Diffusion Bridge Models (SDDBMs), a generalized framework that regularizes diffusion bridges directly at the level of their terminal constraints. Instead of imposing an exact endpoint, SDDBMs prescribe a non-degenerate Gaussian terminal marginal under the transformed path measure, with a flexible terminal center and variance. Starting from this prescribed marginal, we develop a complete closed-form construction of the soft bridge, including the Gaussian terminal reweighting and soft \(h\)-function, the induced Gaussian forward marginals and \(\mathbf{x}_0\)-free dynamics. Theoretically, SDDBMs provide a unified probabilistic perspective that encompasses existing diffusion bridge models, including DDBMs, GOUB, and UniDB, as special cases under specific parameter choices. Extensive experiments on image restoration tasks demonstrate that SDDBMs achieve improved numerical stability and superior generation quality over existing bridge-based methods.

Related papers

• Twisted Schrödinger Bridge Matching [34.126987447337534]
  Diffusion-based Schrdinger bridge models have been proposed to approximate optimal transport dynamics between two prescribed boundary distributions.<n>We introduce Twisted Schrdinger Bridge Matching, a diffusion-based method designed to handle both continuous- and discrete-time potentials.
  arXiv  Detail & Related papers  (2026-07-18T22:30:43Z)
• Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schrödinger Samplers [68.9946633641494]
  Flow matching and Schrdinger bridges define probability, yet their inference grids are usually or inherited from one-endpoint diffusion.<n>We derive a conditional-marginal entropy-rate objective for bridge-aware discretization, separating endpoint-conditioned bridge geometry from marginal flow evolution.<n>On EDM/CIFAR-10, the entropic time-discretization gives the best tested five-step FID (186.3 pm 4.0 versus 200.5 pm 2.9 for linear and 238.0 pm 5.3 for cosine)
  arXiv  Detail & Related papers  (2026-05-15T16:11:10Z)
• Variational Bayesian Flow Network for Graph Generation [54.94088904387278]
  We propose Variational Bayesian Flow Network (VBFN) for graph generation.<n>VBFN performs variational lifting to a tractable joint Gaussian variational belief family governed by structured precisions.<n>On synthetic and molecular graph datasets, VBFN improves fidelity and diversity, and surpasses baseline methods.
  arXiv  Detail & Related papers  (2026-01-30T03:59:38Z)
• Fractional Diffusion Bridge Models [31.569955540169104]
  Fractional Diffusion Bridge Models (FDBM)<n>We present a novel generative diffusion bridge framework driven by an approximation of the rich and non-Markovian fractional Brownian motion (fBM)
  arXiv  Detail & Related papers  (2025-11-03T17:51:10Z)
• Residual Diffusion Bridge Model for Image Restoration [57.31163715170476]
  Diffusion bridge models establish probabilistic paths between arbitrary paired distributions.<n>Most existing methods merely treat them as simple variants of interpolants, lacking a unified analytical perspective.<n>We propose the Residual Diffusion Bridge Model (RDBM) to address these challenges.
  arXiv  Detail & Related papers  (2025-10-27T08:35:49Z)
• Schrödinger bridge for generative AI: Soft-constrained formulation and convergence analysis [6.584866740785309]
  We study the so-called soft-constrained Schr"odinger bridge problem (SCSBP)<n>We prove that as the penalty grows, both the controls and value functions converge to those of the classical SBP at a linear rate.<n>These results provide the first quantitative convergence guarantees for soft-constrained bridges.
  arXiv  Detail & Related papers  (2025-10-13T18:29:15Z)
• Single-Step Bidirectional Unpaired Image Translation Using Implicit Bridge Consistency Distillation [55.45188329646137]
  Implicit Bridge Consistency Distillation (IBCD) enables single-step bidirectional unpaired translation without using adversarial loss.<n>IBCD achieves state-of-the-art performance on benchmark datasets in a single generation step.
  arXiv  Detail & Related papers  (2025-03-19T09:48:04Z)
• UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control [73.73585888013665]
  We propose UniDB, a unified framework for diffusion bridges based on Optimal Control (SOC)<n>UniDB formulates the problem through an SOC-based optimization and derives a closed-form solution for the optimal controller.<n>We demonstrate that existing diffusion bridges employing Doob's $h$-transform constitute a special case of our framework.
  arXiv  Detail & Related papers  (2025-02-09T02:43:57Z)
• Inverse Bridge Matching Distillation [69.479483488685]
  Diffusion bridge models (DBMs) are a promising extension of diffusion models for applications in image-to-image translation.<n>We propose a novel distillation technique based on the inverse bridge matching formulation and derive the tractable objective to solve it in practice.<n>We evaluate our approach for both conditional and unconditional types of bridge matching on a wide set of setups, including super-resolution, JPEG restoration, sketch-to-image, and other tasks.
  arXiv  Detail & Related papers  (2025-02-03T13:56:03Z)
• Discrete Diffusion Schrödinger Bridge Matching for Graph Transformation [1.8257739595540863]
  Transporting arbitrary distributions between arbitrary distributions is a fundamental goal in generative modeling.<n>We propose a novel framework that utilizes continuous-time Markov chains to solve the SB problem in a high-dimensional discrete state space.<n>We show that our framework can effectively optimize molecules' property-of-interest with minimal graph transformation.
  arXiv  Detail & Related papers  (2024-10-02T12:51:25Z)
• Diffusion Bridge Implicit Models [25.213664260896103]
  Denoising diffusion bridge models (DDBMs) are a powerful variant of diffusion models for interpolating between two arbitrary paired distributions.<n>We take the first step in fast sampling of DDBMs without extra training, motivated by the well-established recipes in diffusion models.<n>We induce a novel, simple, and insightful form of ordinary differential equation (ODE) which inspires high-order numerical solvers.
  arXiv  Detail & Related papers  (2024-05-24T19:08:30Z)

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.