mlsanityData to 14 Oct 2026

Simplified Diffusion Schr"odinger Bridge

arXiv 2403.14623 ↗First posted 21 Mar 2024cs.LG cs.CVcited by 4

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

This paper introduces a novel theoretical simplification of the Diffusion Schr"odinger Bridge (DSB) that facilitates its unification with Score-based Generative Models (SGMs), addressing the limitations of DSB in complex data generation and enabling faster convergence and enhanced performance. By employing SGMs as an initial solution for DSB, our approach capitalizes on the strengths of both frameworks, ensuring a more efficient training process and improving the performance of SGM. We also propose a reparameterization technique that, despite theoretical approximations, practically improves the network's fitting capabilities. Our extensive experimental evaluations confirm the effectiveness of the simplified DSB, demonstrating its significant improvements. We believe the contributions of this work pave the way for advanced generative modeling.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 36 of its 53 references that are in the map. First posted on arXiv 21 Mar 2024.

Builds on

36 of 53 references.

Closest ancestors · 14

Same direction, newest first

  1. 2023Common Diffusion Noise Schedules and Sample Steps are Flawed15 May
  2. 2023Diffusion Schr"odinger Bridge Matching29 Mar
  3. 2023Efficient Diffusion Training via Min-SNR Weighting Strategy16 Mar
  4. 2023I2SB: Image-to-Image Schr"odinger Bridge12 Feb
  5. 2023On the Importance of Noise Scheduling for Diffusion Models26 Jan
  6. 2022f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation10 Oct
  7. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  8. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  9. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesis29 Nov
  10. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modeling1 Jun
  11. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  12. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
2 more
  1. 2020Denoising Diffusion Implicit Models6 Oct
  2. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 22

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  3. 2022Flow Matching for Generative Modelingcited by 5,702
  4. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  6. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  7. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  8. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  9. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,778
  10. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
  11. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 931
  12. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 879
10 more
  1. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 699
  2. 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 385
  3. 2013A survey of the Schr"odinger problem and some of its connections with optimal transportcited by 292
  4. 2021Solving Schr"odinger Bridges via Maximum Likelihoodcited by 141
  5. 2019Wasserstein Proximal Algorithms for the Schr"odinger Bridge Problem: Density Control with Nonlinear Driftcited by 50
  6. 2023VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encodercited by 39
  7. 2015Entropic and displacement interpolation: a computational approach using the Hilbert metriccited by 34
  8. 2023Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesiscited by 30
  9. 2018The data-driven Schroedinger bridgecited by 26
  10. 2020Learning normalizing flows from Entropy-Kantorovich potentialscited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

Similar, not cited

Close in wording, no citation either way

  1. 2025Incorporating Pre-trained Diffusion Models in Solving the Schr"odinger Bridge Problem
  2. 2026Foundations of Schr"odinger Bridges for Generative Modeling
  3. 2025A Closed-Form Framework for Schr"odinger Bridges Between Arbitrary Densities
  4. 2026Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schr"odinger Bridge Matching
  5. 2026LightSBB-M: Bridging Schr"odinger and Bass for Generative Diffusion Modeling
  6. 2024Sch"odinger Bridge Type Diffusion Models as an Extension of Variational Autoencoders
  7. 2026Reflected Schr"odinger Bridge Matching
  8. 2026QDSB: Quantized Diffusion Schr"odinger Bridges