Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-Resolution

Yiyang Ma, Huan Yang, Wenhan Yang, Jianlong Fu, Jiaying Liu

Introduction

Diffusion models have emerged as a powerful class of generative models, particularly for tasks like Image Super-Resolution (SR). However, their stochastic nature introduces a "sampling lottery": the quality of the reconstructed high-resolution image depends heavily on the initial random noise vector. This instability often results in inconsistent textures or artifacts, posing a significant challenge for practical applications where reliability is paramount. While most research focuses on retraining models to improve performance, this work explores a different path: identifying an "approximately optimal" starting noise vector to consistently produce high-quality results from pre-trained models without additional training.

Methodology: Finding the "Golden" Starting Point

The researchers propose shifting the perspective from Stochastic Differential Equations (SDEs) to deterministic Diffusion Ordinary Differential Equations (ODEs). In a Diffusion ODE, the path from the initial noise ($x_T$, the boundary condition) to the final image ($x_0$) is fixed. The goal is to find a specific boundary condition, $\tilde{x}_T$, that yields the best perceptual quality across various inputs.

Conceptual overview of finding the approximately optimal boundary condition ($\tilde{x}_T$) to produce high-quality SR samples across different inputs.

The method relies on three key steps:

  1. The Independence Discovery: Bayesian analysis suggests that the "optimal" starting noise is largely independent of the specific low-resolution input image.
  2. Monte Carlo Exploration: A set of noise vectors is randomly sampled and tested against a small reference set of high-resolution/low-resolution image pairs.
  3. Perceptual Selection: The noise vector that consistently minimizes the Learned Perceptual Image Patch Similarity (LPIPS) metric across the reference set is selected as the "approximately optimal" boundary condition ($\tilde{x}_T$).

Experimental Setup

The method was evaluated using standard super-resolution benchmarks. The baseline diffusion models were trained on the DF2k dataset (a combination of DIV2K and Flickr2K). Testing was conducted on DIV2k-test, Urban100 (rich in architectural details), and BSD100. Additionally, the approach was applied to StableSR, demonstrating its effectiveness on real-world degradations using pre-trained Stable Diffusion weights.

Key Results and Insights

The use of an optimal boundary condition provides a significant performance boost for existing diffusion samplers. Notably, it allows faster samplers to outperform slower, stochastic ones. For instance, a 100-step DDIM sampler using the optimal BC achieved an LPIPS score of 0.1032 on DIV2k-test, surpassing the 1000-step DDPM sampler (0.1075) while being ten times faster.

Quantitative comparison of the proposed method against state-of-the-art super-resolution models across standard benchmarks.

Beyond quantitative gains, the method ensures stability. By removing the randomness of the initial seed, the model produces steady, predictable, and high-fidelity images with fewer hallucinated artifacts. This "inference-side" optimization requires no changes to the model's weights, making it a "free" upgrade for pre-trained diffusion systems.

Conclusion and Future Directions

While highly effective, the current method is constrained by image resolution; an optimal noise vector found for a specific resolution (e.g., 256x256) cannot be directly applied to other sizes. Furthermore, the initial search for $\tilde{x}_T$ involves a one-time computational cost. Future research aims to develop "resolution-arbitrary" sampling methods and extend this optimal boundary logic to other image restoration tasks such as colorization and low-light enhancement.

Summary updated

BibTeX
@inproceedings{ma2024solving,
  author = {Yiyang Ma and Huan Yang and Wenhan Yang and Jianlong Fu and Jiaying Liu},
  title = {{Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-Resolution}},
  booktitle = {International Conference on Learning Representations},
  year = {2024},
  url = {https://openreview.net/forum?id=BtT6o5tfHu},
}
Figure