用低秩残差构建小型可解释3D查表，提升图像调色质量
LoR-LUT: Learning Compact 3D Lookup Tables via Low-Rank Residuals
- 通过低秩残差与基础查表联合生成紧凑3D LUT
- 在亚兆字节模型下实现专家级调色效果
- 支持交互式调节，提升结果可解释性
我们提出LoR-LUT，一种统一的低秩框架，用于生成紧凑且可解释的3D查找表（LUT）。不同于依赖密集基底LUT的传统方法，该方法联合使用低秩残差修正与一组基底LUT，显著提升图像感知质量。在保持三线性插值复杂度的同时，大幅减少网络、残差修正及LUT参数量。基于MIT-Adobe FiveK数据集训练的实验表明，该方法以小于1MB的模型尺寸，实现了专家级调色特征和高感知保真度。此外，我们开发了交互式可视化工具LoR-LUT Viewer，通过滑块控制参数，实时将输入图像转换为调整后的输出，有效增强结果可解释性和用户信心。整体上，该方法为未来基于LUT的图像增强与风格迁移提供了紧凑、可解释且高效的新方向。
原文摘要 · Abstract (English)
We present LoR-LUT, a unified low-rank formulation for compact and interpretable 3D lookup table (LUT) generation. Unlike conventional 3D-LUT-based techniques that rely on fusion of basis LUTs, which are usually dense tensors, our unified approach extends the current framework by jointly using residual corrections, which are in fact low-rank tensors, together with a set of basis LUTs. The approach described here improves the existing perceptual quality of an image, which is primarily due to the technique's novel use of residual corrections. At the same time, we achieve the same level of trilinear interpolation complexity, using a significantly smaller number of network, residual corrections, and LUT parameters. The experimental results obtained from LoR-LUT, which is trained on the MIT-Adobe FiveK dataset, reproduce expert-level retouching characteristics with high perceptual fidelity and a sub-megabyte model size. Furthermore, we introduce an interactive visualization tool, termed LoR-LUT Viewer, which transforms an input image into the LUT-adjusted output image, via a number of slidebars that control different parameters. The tool provides an effective way to enhance interpretability and user confidence in the visual results. Overall, our proposed formulation offers a compact, interpretable, and efficient direction for future LUT-based image enhancement and style transfer.
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。