ChameleonTuner: Automatic ISP Color Tuning in Subjective Scenarios

Image color enhancement is a key component of ISP pipelines, with 3D LUTs widely adopted for nonlinear color transformations and color refinement. Existing learning-based approaches attempt to learn a global mapping from paired pixel-aligned training samples, but this offers limited control and flexibility for practitioners and restricts adaptation to specific images or scenarios. Moreover, the assumption of pixel-aligned supervision requires costly manual retouching to generate ground-truth references. A practical alternative is to use DSLR images as high-quality references, but the inevitable FoV and PoV variations make pixel-level 3D LUT calibration unreliable. We propose ChameleonTuner, a novel framework that establishes region-level color correspondences to handle FoV/PoV discrepancies. Unlike prior learning-based 3D LUT methods, the proposed framework defines a dedicated search space for LUT tuning and employs multi-objective search to achieve controllable and interpretable optimization. Extensive experiments across multiple perceptual color metrics demonstrate that our method is effective in subjective scenarios (e.g., DPED) with geometric misalignments, while remaining competitive on standard pixel-aligned benchmarks (e.g., MIT-Adobe FiveK). Our code is available at https://github.com/ZjTan4/ ChameleonTuner.git.