Energy-oriented Diffusion Bridge for Image Restoration with Foundational Diffusion Models

2026-04-13

AI Summary

This work addresses the limitations of existing diffusion bridge models in image restoration, which rely on high-cost trajectories that compromise sampling efficiency and reconstruction quality. To overcome this, the authors propose an energy-guided diffusion bridge (E-Bridge) framework that constructs geodesic trajectories on low-energy manifolds, enabling efficient restoration within a shortened time span. The method incorporates an entropy-regularized initial state to reduce trajectory energy requirements, learns a single-step mapping function through a continuous-time consistency objective, and introduces an adjustable trajectory length mechanism that adapts to diverse degradation tasks. Experimental results demonstrate that E-Bridge achieves state-of-the-art performance across multiple image restoration benchmarks, supporting high-quality reconstruction in either a single step or very few steps.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Learning with Manifolds
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Diffusion bridge models have shown great promise in image restoration by explicitly connecting clean and degraded image distributions. However, they often rely on complex and high-cost trajectories, which limit both sampling efficiency and final restoration quality. To address this, we propose an Energy-oriented diffusion Bridge (E-Bridge) framework to approximate a set of low-cost manifold geodesic trajectories to boost the performance of the proposed method. We achieve this by designing a novel bridge process that evolves over a shorter time horizon and makes the reverse process start from an entropy-regularized point that mixes the degraded image and Gaussian noise, which theoretically reduces the required trajectory energy. To solve this process efficiently, we draw inspiration from consistency models to learn a single-step mapping function, optimized via a continuous-time consistency objective tailored for our trajectory, so as to analytically map any state on the trajectory to the target image. Notably, the trajectory length in our framework becomes a tunable task-adaptive knob, allowing the model to adaptively balance information preservation against generative power for tasks of varying degradation, such as denoising versus super-resolution. Extensive experiments demonstrate that our E-Bridge achieves state-of-the-art performance across various image restoration tasks while enabling high-quality recovery with a single or fewer sampling steps. Our project page is https://jinnh.github.io/E-Bridge/.

Problem

• image restoration
• diffusion bridge
• sampling efficiency
• trajectory cost
• restoration quality

Innovation

• Energy-oriented Diffusion
• Diffusion Bridge
• Consistency Model
• Manifold Geodesic Trajectory
• Task-adaptive Sampling