Pith. sign in

REVIEW 17 cited by

Denoising Diffusion Bridge Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2309.16948 v3 pith:SRNAKZCF submitted 2023-09-29 cs.CV cs.AI

Linqi Zhou , Aaron Lou , Samar Khanna , Stefano Ermon This is my paper · ORCID
classification cs.CVcs.AI
keywords diffusionmodelsddbmsimagebridgedistributiongenerativemethods
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Diffusion models are powerful generative models that map noise to data using stochastic processes. However, for many applications such as image editing, the model input comes from a distribution that is not random noise. As such, diffusion models must rely on cumbersome methods like guidance or projected sampling to incorporate this information in the generative process. In our work, we propose Denoising Diffusion Bridge Models (DDBMs), a natural alternative to this paradigm based on diffusion bridges, a family of processes that interpolate between two paired distributions given as endpoints. Our method learns the score of the diffusion bridge from data and maps from one endpoint distribution to the other by solving a (stochastic) differential equation based on the learned score. Our method naturally unifies several classes of generative models, such as score-based diffusion models and OT-Flow-Matching, allowing us to adapt existing design and architectural choices to our more general problem. Empirically, we apply DDBMs to challenging image datasets in both pixel and latent space. On standard image translation problems, DDBMs achieve significant improvement over baseline methods, and, when we reduce the problem to image generation by setting the source distribution to random noise, DDBMs achieve comparable FID scores to state-of-the-art methods despite being built for a more general task.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 17 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution

    cs.CV 2024-12 conditional novelty 7.0 of 10

    CrossFlow turns text directly into images, and images into text, depth, and higher resolution, by flowing between modality latents without a noise prior or cross-attention.

  2. GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors

    cs.CV 2026-08 conditional novelty 6.0 of 10

    Starting flow-matching video generation from a depth-warped reference frame with spatially-adaptive noise injection reduces required sampling steps by about five times on NuScenes driving videos.

  3. AtomDiffuser: Time-Aware Degradation Modeling for Drift and Beam Damage in STEM Imaging

    cs.CV 2025-08 conditional novelty 6.0 of 10

    AtomDiffuser predicts affine drift and spatially varying beam damage between STEM image frames, trained on synthetic degradation and shown qualitatively on real cryo-STEM data.

  4. TrajDiff: Diffusion Bridge Network with Semantic Alignment for Trajectory Similarity Computation

    cs.LG 2025-06 conditional novelty 6.0 of 10

    TrajDiff combines semantic alignment attention, DDBM-based pretraining, and listwise ranking losses to achieve state-of-the-art approximate trajectory similarity on Porto, Geolife, and T-Drive.

  5. IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion Models

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A Gaussian-path transition equation lets a pretrained Stable Diffusion model serve as the denoiser inside image restoration bridges, cutting per-task training to a lightweight ControlNet.

  6. Training-Free Multi-Step Audio Source Separation

    cs.SD 2025-05 conditional novelty 6.0 of 10

    Iteratively remixing and re-separating the input mixture, with the best blend chosen by a quality metric, improves pretrained one-step audio separation models without any retraining.

  7. MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schr\"odinger Bridges

    cs.CR 2025-05 conditional novelty 6.0 of 10

    MixBridge injects multiple backdoor triggers into image-to-image Schrödinger bridge models by training on poisoned pairs and merging task-specific experts, achieving high attack success and stealthy weights.

  8. UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A stochastic optimal control formulation of diffusion bridges, where Doob's h-transform is the infinite-penalty limit and a finite penalty yields a tunable detail-preserving bridge.

  9. An Ordinary Differential Equation Sampler with Stochastic Start for Diffusion Bridge Models

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A stochastic-start ODE sampler for diffusion bridge models avoids the singular start of the probability-flow ODE and beats prior samplers with fewer neural network evaluations.

  10. Real-time One-Step Diffusion-based Expressive Portrait Videos Generation

    cs.CV 2024-12 conditional novelty 6.0 of 10

    OSA-LCM distills a portrait video diffusion model into a single-step generator that matches the quality of a 20-step teacher on FID/FVD, enabling near real-time talking-head generation.

  11. Pharmacophore-guided de novo drug design with diffusion bridge

    q-bio.BM 2024-12 conditional novelty 6.0 of 10

    PharmacoBridge, an SE(3)-equivariant diffusion bridge, generates valid 3D drug-like molecules directly from pharmacophore point clouds and outperforms pocket-based baselines in pharmacophore matching and docking affin...

  12. Translationese as a Rational Response to Translation Task Difficulty

    cs.CL 2026-03 unverdicted novelty 5.0 of 10

    Translationese is partly predictable from quantifiable translation-task difficulty, especially cross-lingual transfer load, more so for English-to-German than the reverse.

  13. Dual guidance: ROM-informed field reconstruction with generative models

    physics.flu-dyn 2025-06 conditional novelty 5.0 of 10

    Optimized mutual-information sensor placement improves sparse-sensor reconstruction of cylinder-wake flows with a guided diffusion model, but the gains vanish beyond about 25 sensors.

  14. Diffusion Bridge or Flow Matching? A Unifying Framework and Comparative Analysis

    cs.CV 2025-09 reject novelty 4.0 of 10

    A theoretical and empirical comparison claiming diffusion bridges have lower stochastic-optimal-control cost and greater robustness than flow matching when training data are scarce.

  15. Diffusion Bridge Models for 3D Medical Image Translation

    cs.CV 2025-04 conditional novelty 4.0 of 10

    A diffusion bridge model generates 3D T1-to-FA and FA-to-T1 brain images on ADNI data, with downstream classification accuracy close to real images.

  16. Force Matching with Relativistic Constraints: A Physics-Inspired Approach to Stable and Efficient Generative Modeling

    cs.LG 2025-02 reject novelty 4.0 of 10

    Force Matching replaces velocity matching in flow-based generative models with a relativistic force objective, but the toy experiments are designed so the model class matches the data generator exactly.

  17. Diffusion Prism: Enhancing Diversity and Morphology Consistency in Mask-to-Image Diffusion

    cs.CV 2025-01 conditional novelty 4.0 of 10

    Adding small amounts of Gaussian noise and chromatic aberration to binary masks before image-to-image diffusion increases output diversity without losing morphological structure.

Pith tools