DCDB: Dynamic Conditional Dual Diffusion Bridge for Ill-posed Multi-Tasks
Conditional diffusion models have made impressive progress in the field of image processing, but the characteristics of constructing data distribution pathways make it difficult to exploit the intrinsic correlation between tasks in multi-task scenarios, which is even worse in ill-posed tasks with a lack of training data. In addition, traditional static condition control makes it difficult for networks to learn in multi-task scenarios with its dynamically evolving characteristics. To address these challenges, we propose a dynamic conditional double diffusion bridge training paradigm to build a general framework for ill-posed multi-tasks. Firstly, this paradigm decouples the diffusion and condition generation processes, avoiding the dependence of the diffusion model on supervised data in ill-posed tasks. Secondly, generated by the same noise schedule, dynamic conditions are used to gradually adjust their statistical characteristics, naturally embed time-related information, and reduce the difficulty of network learning. We analyze the learning objectives of the network under different conditional forms in the single-step denoising process and compare the changes in its attention weights in the network, demonstrating the superiority of our dynamic conditions. Taking dehazing and visible-infrared fusion as typical ill-posed multi-task scenarios, we achieve the best performance in multiple indicators on public datasets. The code has been publicly released at: https://anonymous.4open.science/r/DCDB-D3C2.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Spherical Brownian Bridge Diffusion Models for Conditional Cortical Thickness Forecasting
Accurate forecasting of individualized, high-resolution cortical thickness (CTh) trajectories is essential for detecting subtle cortical changes, providing invaluable insights into neurodegenerative processes and facilit…
Conditional Diffusion Model for Multi-Agent Dynamic Task Decomposition
Task decomposition has shown promise in complex cooperative multi-agent reinforcement learning (MARL) tasks, which enables efficient hierarchical learning for long-horizon tasks in dynamic and uncertain environments. How…
Multi-agent Reinforcement LearningConditional Simulation Using Diffusion Schrödinger Bridges
Denoising diffusion models have recently emerged as a powerful class of generative models. They provide state-of-the-art results, not only for unconditional simulation, but also when used to solve conditional simulation …
DeblurringDenoisingImage InpaintingImage Super-Resolution+2Enhanced Control for Diffusion Bridge in Image Restoration
Image restoration refers to the process of restoring a damaged low-quality image back to its corresponding high-quality image. Typically, we use convolutional neural networks to directly learn the mapping from low-qualit…
DenoisingImage RestorationRain RemovalSuper-ResolutionLeveraging Priors via Diffusion Bridge for Time Series Generation
Time series generation is widely used in real-world applications such as simulation, data augmentation, and hypothesis test techniques. Recently, diffusion models have emerged as the de facto approach for time series gen…
Data AugmentationTime SeriesTime Series Generation