REVIEW 8 cited by
Denoising Diffusion Bridge Models
Not yet reviewed by Pith; the record is open.
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
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.
Forward citations
Cited by 8 Pith papers
-
AtomDiffuser: Time-Aware Degradation Modeling for Drift and Beam Damage in STEM Imaging
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.
-
TrajDiff: Diffusion Bridge Network with Semantic Alignment for Trajectory Similarity Computation
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.
-
IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion Models
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.
-
Training-Free Multi-Step Audio Source Separation
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.
-
UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control
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.
-
Translationese as a Rational Response to Translation Task Difficulty
Translationese is partly predictable from quantifiable translation-task difficulty, especially cross-lingual transfer load, more so for English-to-German than the reverse.
-
Diffusion Bridge or Flow Matching? A Unifying Framework and Comparative Analysis
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.
-
Force Matching with Relativistic Constraints: A Physics-Inspired Approach to Stable and Efficient Generative Modeling
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.
Discussion (0). Continue with ORCID to comment.