直接在JPEG压缩域进行图像超分，提速近2.5倍且画质不降。
Learning Single-Image Super-Resolution in the JPEG Compressed Domain
- 在JPEG的DCT系数域直接训练超分模型，跳过完整解码
- 数据加载速度提升2.6倍，训练速度提升2.5倍
- 适合需要高效推理的部署场景，如移动端
深度学习模型日益复杂，输入数据规模随之增长。尽管专用硬件有显著进步，数据加载仍是制约训练与推理速度的主要瓶颈。为解决此问题，我们提出直接在编码后的JPEG特征上训练模型，减少完整JPEG解码带来的计算开销，显著提升数据加载效率。以往研究多关注识别任务，而本文探索该方法在单图像超分辨率（SISR）恢复任务中的有效性。我们构建了一个轻量级超分流程，直接在频率域操作JPEG的离散余弦变换（DCT）系数。该方法实现数据加载速度2.6倍提升和训练速度2.5倍加速，同时保持与标准SISR方法相当的视觉质量。
原文摘要 · Abstract (English)
Deep learning models have grown increasingly complex, with input data sizes scaling accordingly. Despite substantial advances in specialized deep learning hardware, data loading continues to be a major bottleneck that limits training and inference speed. To address this challenge, we propose training models directly on encoded JPEG features, reducing the computational overhead associated with full JPEG decoding and significantly improving data loading efficiency. While prior works have focused on recognition tasks, we investigate the effectiveness of this approach for the restoration task of single-image super-resolution (SISR). We present a lightweight super-resolution pipeline that operates on JPEG discrete cosine transform (DCT) coefficients in the frequency domain. Our pipeline achieves a 2.6x speedup in data loading and a 2.5x speedup in training, while preserving visual quality comparable to standard SISR approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。