paper-with-me

Papers

Neural Guided Diffusion Bridges

2025-02-17 · Gefan Yang, Frank van der Meulen, Stefan Sommer

We propose a novel method for simulating conditioned diffusion processes (diffusion bridges) in Euclidean spaces. By training a neural network to approximate bridge dynamics, our approach eliminates the need for computationally intensive Markov Chain Monte Carlo (MCMC) methods or reverse-process modeling. Compared to existing methods, it offers greater robustness across various diffusion specifications and conditioning scenarios. This applies in particular to rare events and multimodal distributions, which pose challenges for score-learning- and MCMC-based approaches. We propose a flexible variational family for approximating the diffusion bridge path measure which is partially specified by a neural network. Once trained, it enables efficient independent sampling at a cost comparable to sampling the unconditioned (forward) process.

📄 PDF Abstract BibTeX arXiv:2502.11909

Code (1)

bookdiver/neuralbridge 공식 구현 jax

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model

2024-03-26 · CVPR 2024 1 · Runmin Dong, Shuai Yuan, Bin Luo, Mengxuan Chen 외

Reference-based super-resolution (RefSR) has the potential to build bridges across spatial and temporal resolutions of remote sensing images. However, existing RefSR methods are limited by the faithfulness of content rec…

DenoisingReference-based Super-ResolutionSuper-Resolution

Latent Space Synergy: Text-Guided Data Augmentation for Direct Diffusion Biomedical Segmentation

2025-07-21 · Muhammad Aqeel, Maham Nazir, Zanxi Ruan, Francesco Setti arxiv

Medical image segmentation suffers from data scarcity, particularly in polyp detection where annotation requires specialized expertise. We present SynDiff, a framework combining text-guided synthetic data generation with…

Medical Image SegmentationSynthetic Data GenerationData Augmentation

Structured Diffusion Bridges: Inductive Bias for Denoising Diffusion Bridges

2026-05-03 · Eitan Kosman, Gabriele Serussi, Chaim Baskin arxiv

Modality translation is inherently under-constrained, as multiple cross-modal mappings may yield the same marginals. Recent work has shown that diffusion bridges are effective for this task. However, most existing approa…

Towards Controllable Diffusion Models via Reward-Guided Exploration

2023-04-14 · Hengtong Zhang, Tingyang Xu

By formulating data samples' formation as a Markov denoising process, diffusion models achieve state-of-the-art performances in a collection of tasks. Recently, many variants of diffusion models have been proposed to ena…

DenoisingReinforcement Learning (RL)

Rethinking Losses for Diffusion Bridge Samplers

2025-06-12 · Sebastian Sanokowski, Lukas Gruber, Christoph Bartmann, Sepp Hochreiter 외

Diffusion bridges are a promising class of deep-learning methods for sampling from unnormalized distributions. Recent works show that the Log Variance (LV) loss consistently outperforms the reverse Kullback-Leibler (rKL)…

Hyperparameter Optimization