Search papers, labs, and topics across Lattice.
This paper introduces StatLUT, a novel multimodal framework for generating 3D Look-Up Tables (LUTs) that enhances photorealistic style transfer by decoupling color distributions from structural semantics. By employing a Lab-Extractor to derive spatially-agnostic statistical features and formulating LUT generation as a Transformer-based Seq2Seq task, the authors effectively mitigate common issues such as semantic entanglement and color banding. Extensive evaluations reveal that StatLUT outperforms existing methods in both visual quality and quantitative metrics, marking a significant advancement in multimodal style transfer techniques.
StatLUT achieves artifact-free photorealistic style transfer by decoupling color and structure, outperforming state-of-the-art methods in visual fidelity.
Photorealistic Style Transfer (PST) aims to transfer the color and tonal style of a reference to a content image while strictly preserving its structural integrity. However, existing deep learning-based methods inherently suffer from semantic entanglement caused by pre-trained image encoders, leading to unnatural spatial distortions. Moreover, current pixel-level mapping paradigms often ignore color gamut topology, resulting in color banding, while also lacking the multimodal capability for intuitive text-driven control. To address these bottlenecks, we propose StatLUT, an innovative multimodal framework for 3D LUT generation. First, we bypass traditional encoders and introduce a Lab-Extractor to derive spatially-agnostic statistical features, fundamentally decoupling color distributions from structural semantics to ensure artifact-free rendering. Second, we formulate LUT generation as a Transformer-based Seq2Seq translation task, utilizing a Multi-dimensional Residual Mapper (MR-Mapper) to predict topologically smooth 3D LUTs. Finally, to break the single-modal barrier, we propose the H-Diffuser, a lightweight Diffusion Transformer that directly synthesizes statistical features from natural language prompts, enabling flexible text-driven color grading. Extensive experiments on standard benchmarks demonstrate that StatLUT significantly outperforms state-of-the-art methods in both visual quality and quantitative metrics, pioneering a highly robust and flexible paradigm for multimodal photorealistic style transfer.
