Trang chủ / Tin tức / Khoa học & công nghệ
Khoa học & công nghệ

Preserve More Details: Mitigating Content Drift in Real-World Image Super-Resolution

06/11/2026 · Thành viên: PGS.TS Trần Thanh Sơn · Nguồn: OpenAlex

Real-world image super-resolution (Real-ISR) aims to reconstruct high-quality (HQ) images from low-quality (LQ) inputs subject to diverse real-world degradations. Recent advances have leveraged the...

<p><strong>Tác giả:</strong> Chunxiao Liu, Wei Liu, Anbin Xiong, Erli Meng</p>

<p>Real-world image super-resolution (Real-ISR) aims to reconstruct high-quality (HQ) images from low-quality (LQ) inputs subject to diverse real-world degradations. Recent advances have leveraged the LQ inputs and natural image priors learned by Stable Diffusion models to achieve impressive results. However, existing methods often overlook insufficient clarity of LQ inputs inevitably induce content drift in the generated HQ images. This manifests primarily as visual detail degradation and textu...</p>

<p>📄 DOI: <a href="https://doi.org/https://doi.org/10.1145/3767308.3835295" target="_blank" rel="noopener">https://doi.org/10.1145/3767308.3835295</a></p>

<p>📖 <a href="https://doi.org/https://doi.org/10.1145/3767308.3835295" target="_blank" rel="noopener">Xem bài báo đầy đủ</a></p>

Bài viết được biên soạn lại bởi LIFVietnam. Nguồn tham khảo: OpenAlex