CVIVDec 11, 2025

Learning from a Generative Oracle: Domain Adaptation for Restoration

arXiv:2512.11121v1
AI Analysis

This addresses the domain adaptation challenge for image restoration in practical scenarios, offering an incremental improvement over existing methods.

The paper tackles the problem of adapting pre-trained image restoration models to real-world, out-of-distribution degradations without paired data, achieving significant performance improvements on diverse benchmarks.

Pre-trained image restoration models often fail on real-world, out-of-distribution degradations due to significant domain gaps. Adapting to these unseen domains is challenging, as out-of-distribution data lacks ground truth, and traditional adaptation methods often require complex architectural changes. We propose LEGO (Learning from a Generative Oracle), a practical three-stage framework for post-training domain adaptation without paired data. LEGO converts this unsupervised challenge into a tractable pseudo-supervised one. First, we obtain initial restorations from the pre-trained model. Second, we leverage a frozen, large-scale generative oracle to refine these estimates into high-quality pseudo-ground-truths. Third, we fine-tune the original model using a mixed-supervision strategy combining in-distribution data with these new pseudo-pairs. This approach adapts the model to the new distribution without sacrificing its original robustness or requiring architectural modifications. Experiments demonstrate that LEGO effectively bridges the domain gap, significantly improving performance on diverse real-world benchmarks.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes