Neural Guided Diffusion Bridges
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.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model
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-ResolutionLatent Space Synergy: Text-Guided Data Augmentation for Direct Diffusion Biomedical Segmentation
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 AugmentationStructured Diffusion Bridges: Inductive Bias for Denoising Diffusion Bridges
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
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
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