3-D Room Dataset

v1

2024-06-29 12:06pm

Generated on Jun 29, 2024

Dataset Split

Train Set 88%
393Images
Valid Set 8%
37Images
Test Set 4%
19Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Saturation: Between -25% and +25%
Noise: Up to 0.22% of pixels