LoR-LUT: Learning Compact 3D Lookup Tables via Low-Rank Residuals

2026-02-25

AI Summary

This work addresses the limitations of traditional 3D lookup table (LUT)-based image enhancement methods, which rely on dense base LUT fusion and suffer from large model size and poor interpretability, making it difficult to balance efficiency and image quality. To overcome these issues, we propose a unified low-rank residual LUT framework that replaces dense fusion with a low-rank residual correction mechanism. This approach significantly reduces model size while improving perceptual quality, all without increasing the computational complexity of trilinear interpolation. Our method achieves expert-level retouching performance on the MIT-Adobe FiveK dataset with a model under 1 MB, offering high fidelity, real-time inference, and enhanced interpretability. Furthermore, we introduce an interactive visualization tool, LoR-LUT Viewer, to improve user control and trust in the editing process.

Technology Category

• Computer Vision: Large Vision Models
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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.

Problem

• 3D Lookup Table
• Image Enhancement
• Compact Representation
• Interpretability
• Style Transfer

Innovation

• low-rank residuals
• 3D lookup table
• image enhancement
• compact model
• interpretable LUT