Bidirectional Diffusion Bridge Models

• URL: http://arxiv.org/abs/2502.09655v1
• Date: Wed, 12 Feb 2025 04:43:02 GMT
• Title: Bidirectional Diffusion Bridge Models
• Authors: Duc Kieu, Kien Do, Toan Nguyen, Dang Nguyen, Thin Nguyen,
• Abstract summary: Diffusion bridges have shown potential in paired image-to-image (I2I) translation tasks. Existing methods are limited by their unidirectional nature, requiring separate models for forward and reverse translations. We introduce the Bidirectional Diffusion Bridge Model (BDBM), a scalable approach that facilitates bidirectional translation between two coupled distributions.
• Score: 14.789137197695654
• License:
• Abstract: Diffusion bridges have shown potential in paired image-to-image (I2I) translation tasks. However, existing methods are limited by their unidirectional nature, requiring separate models for forward and reverse translations. This not only doubles the computational cost but also restricts their practicality. In this work, we introduce the Bidirectional Diffusion Bridge Model (BDBM), a scalable approach that facilitates bidirectional translation between two coupled distributions using a single network. BDBM leverages the Chapman-Kolmogorov Equation for bridges, enabling it to model data distribution shifts across timesteps in both forward and backward directions by exploiting the interchangeability of the initial and target timesteps within this framework. Notably, when the marginal distribution given endpoints is Gaussian, BDBM's transition kernels in both directions possess analytical forms, allowing for efficient learning with a single network. We demonstrate the connection between BDBM and existing bridge methods, such as Doob's h-transform and variational approaches, and highlight its advantages. Extensive experiments on high-resolution I2I translation tasks demonstrate that BDBM not only enables bidirectional translation with minimal additional cost but also outperforms state-of-the-art bridge models. Our source code is available at [https://github.com/kvmduc/BDBM||https://github.com/kvmduc/BDBM].

Related papers

• Inverse Bridge Matching Distillation [69.479483488685]
  Diffusion bridge models (DBMs) are a promising extension of diffusion models for applications in image-to-image translation. We propose a novel distillation technique based on the inverse bridge matching formulation and derive the tractable objective to solve it in practice. 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)
• Latent Schrodinger Bridge: Prompting Latent Diffusion for Fast Unpaired Image-to-Image Translation [58.19676004192321]
  Diffusion models (DMs), which enable both image generation from noise and inversion from data, have inspired powerful unpaired image-to-image (I2I) translation algorithms. We tackle this problem with Schrodinger Bridges (SBs), which are differential equations (SDEs) between distributions with minimal transport cost. Inspired by this observation, we propose Latent Schrodinger Bridges (LSBs) that approximate the SB ODE via pre-trained Stable Diffusion. We demonstrate that our algorithm successfully conduct competitive I2I translation in unsupervised setting with only a fraction of cost required by previous DM-
  arXiv  Detail & Related papers  (2024-11-22T11:24:14Z)
• Consistency Diffusion Bridge Models [25.213664260896103]
  Diffusion bridge models (DDBMs) build processes between fixed data endpoints based on a reference diffusion process. DDBMs' sampling process typically requires hundreds of network evaluations to achieve decent performance. We propose two paradigms: consistency bridge distillation and consistency bridge training, which is flexible to apply on DDBMs with broad design choices.
  arXiv  Detail & Related papers  (2024-10-30T02:04:23Z)
• BM$^2$: Coupled Schrödinger Bridge Matching [4.831663144935879]
  We propose a non-iterative approach for learning Schr"odinger bridges with neural networks. A preliminary theoretical analysis of the convergence properties of BM$2$ is carried out, supported by numerical experiments.
  arXiv  Detail & Related papers  (2024-09-14T08:57:46Z)
• 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. We take the first step in fast sampling of DDBMs without extra training, motivated by the well-established recipes in diffusion models. 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)
• Unpaired Image-to-Image Translation via Neural Schr\"odinger Bridge [70.79973551604539]
  We propose Unpaired Neural Schr"odinger Bridge (UNSB), which expresses the SB problem as a sequence of adversarial learning problems. UNSB is scalable and successfully solves various unpaired I2I translation tasks.
  arXiv  Detail & Related papers  (2023-05-24T12:05:24Z)
• On the Role of Bidirectionality in Language Model Pre-Training [85.14614350372004]
  We study the role of bidirectionality in next token prediction, text infilling, zero-shot priming and fine-tuning. We train models with up to 6.7B parameters, and find differences to remain consistent at scale.
  arXiv  Detail & Related papers  (2022-05-24T02:25:05Z)
• BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models [50.39417112077254]
  A novel image-to-image translation method based on the Brownian Bridge Diffusion Model (BBDM) is proposed. To the best of our knowledge, it is the first work that proposes Brownian Bridge diffusion process for image-to-image translation.
  arXiv  Detail & Related papers  (2022-05-16T13:47:02Z)
• Dual Diffusion Implicit Bridges for Image-to-Image Translation [104.59371476415566]
  Common image-to-image translation methods rely on joint training over data from both source and target domains. We present Dual Diffusion Implicit Bridges (DDIBs), an image translation method based on diffusion models. DDIBs allow translations between arbitrary pairs of source-target domains, given independently trained diffusion models on respective domains.
  arXiv  Detail & Related papers  (2022-03-16T04:10:45Z)

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.