LuxRemix Dataset

Overview

The LuxRemix dataset is a synthetic dataset of 12K indoor scenes with per-light decomposition, which is designed for training models that decompose and re-mix indoor illumination from a single image.

For more dataset information and example usage scripts, please refer to https://github.com/facebookresearch/luxremix-dataset.

Citation

If you use this dataset, or the accompanying processed data, models, or code, please cite:

LuxRemix: Lighting Decomposition and Remixing for Indoor Scenes
Ruofan Liang, Norman Müller, Ethan Weber, Duncan Zauss, Nandita Vijaykumar, Peter Kontschieder and Christian Richardt
Conference on Computer Vision and Pattern Recognition (CVPR) 2026
https://luxremix.github.io