VIDIT Dataset

This is a version of the VIDIT dataset equipped for training ControlNet using depth maps conditioning. VIDIT includes 390 different Unreal Engine scenes, each captured with 40 illumination settings, resulting in 15,600 images. The illumination settings are all the combinations of 5 color temperatures (2500K, 3500K, 4500K, 5500K and 6500K) and 8 light directions (N, NE, E, SE, S, SW, W, NW). Original image resolution is 1024x1024. We include in this version only the training split containing only 300 scenes. Captions were generated using the BLIP-2, Flan T5-xxl model. Depth maps were generated using the GLPN fine-tuned on NYUv2 model.

Examples with varying direction

Examples with varying color temperature

Disclaimer

I do not own any of this data.