Scenes shipped with the structure-control inputs a guided-generation model consumes (Canny, depth, normal, segmentation, scribble, line-art, and pose) each derived from the same colour ground truth so outputs can be scored against their source.
Colour ground-truth for the mug conditioning suite. Every map in this group is derived from this exact image, so a guided model's output can be scored against it.
Binary Canny edge map extracted from the ground truth — feed as a structure-control input and score the generated result against the reference.
Synthetic depth map (near = bright) for depth-conditioned generation and monocular depth-estimation regression against a known reference.
Tangent-space surface-normal map encoded from the scene depth — a normal-conditioning input for guided generation and relighting tests.
Semantic segmentation map (subject vs background) — the label reference for segmentation-conditioned generation and mask-quality scoring.
Sparse scribble derived from the edges — the loose hand-drawn control input for scribble-guided image generation.
Clean line-art extraction (black lines on white) for line-art-conditioned generation and line-extraction quality tests.
Colour ground-truth for the apple conditioning suite. Every map in this group is derived from this exact image, so a guided model's output can be scored against it.
Binary Canny edge map extracted from the ground truth — feed as a structure-control input and score the generated result against the reference.
Synthetic depth map (near = bright) for depth-conditioned generation and monocular depth-estimation regression against a known reference.
Tangent-space surface-normal map encoded from the scene depth — a normal-conditioning input for guided generation and relighting tests.
Semantic segmentation map (subject vs background) — the label reference for segmentation-conditioned generation and mask-quality scoring.
Sparse scribble derived from the edges — the loose hand-drawn control input for scribble-guided image generation.
Clean line-art extraction (black lines on white) for line-art-conditioned generation and line-extraction quality tests.
Colour ground-truth for the plant conditioning suite. Every map in this group is derived from this exact image, so a guided model's output can be scored against it.
Binary Canny edge map extracted from the ground truth — feed as a structure-control input and score the generated result against the reference.
Synthetic depth map (near = bright) for depth-conditioned generation and monocular depth-estimation regression against a known reference.
Tangent-space surface-normal map encoded from the scene depth — a normal-conditioning input for guided generation and relighting tests.
Semantic segmentation map (subject vs background) — the label reference for segmentation-conditioned generation and mask-quality scoring.
Sparse scribble derived from the edges — the loose hand-drawn control input for scribble-guided image generation.
Clean line-art extraction (black lines on white) for line-art-conditioned generation and line-extraction quality tests.
Colour ground-truth for the robot conditioning suite. Every map in this group is derived from this exact image, so a guided model's output can be scored against it.
Binary Canny edge map extracted from the ground truth — feed as a structure-control input and score the generated result against the reference.
Synthetic depth map (near = bright) for depth-conditioned generation and monocular depth-estimation regression against a known reference.
Tangent-space surface-normal map encoded from the scene depth — a normal-conditioning input for guided generation and relighting tests.
Semantic segmentation map (subject vs background) — the label reference for segmentation-conditioned generation and mask-quality scoring.
Sparse scribble derived from the edges — the loose hand-drawn control input for scribble-guided image generation.
Clean line-art extraction (black lines on white) for line-art-conditioned generation and line-extraction quality tests.
OpenPose-style keypoint skeleton for the figure — a pose-control input for guided generation and a target for pose-estimation checks.
Colour ground-truth for the cat conditioning suite. Every map in this group is derived from this exact image, so a guided model's output can be scored against it.
Binary Canny edge map extracted from the ground truth — feed as a structure-control input and score the generated result against the reference.
Synthetic depth map (near = bright) for depth-conditioned generation and monocular depth-estimation regression against a known reference.
Tangent-space surface-normal map encoded from the scene depth — a normal-conditioning input for guided generation and relighting tests.
Semantic segmentation map (subject vs background) — the label reference for segmentation-conditioned generation and mask-quality scoring.
Sparse scribble derived from the edges — the loose hand-drawn control input for scribble-guided image generation.
Clean line-art extraction (black lines on white) for line-art-conditioned generation and line-extraction quality tests.
OpenPose-style keypoint skeleton for the figure — a pose-control input for guided generation and a target for pose-estimation checks.
Colour ground-truth for the fruit conditioning suite. Every map in this group is derived from this exact image, so a guided model's output can be scored against it.
Binary Canny edge map extracted from the ground truth — feed as a structure-control input and score the generated result against the reference.
Synthetic depth map (near = bright) for depth-conditioned generation and monocular depth-estimation regression against a known reference.
Tangent-space surface-normal map encoded from the scene depth — a normal-conditioning input for guided generation and relighting tests.
Semantic segmentation map (subject vs background) — the label reference for segmentation-conditioned generation and mask-quality scoring.
Sparse scribble derived from the edges — the loose hand-drawn control input for scribble-guided image generation.
Clean line-art extraction (black lines on white) for line-art-conditioned generation and line-extraction quality tests.
We use Google Analytics and show ads via Adsterra. Non-essential cookies and ad scripts run only after you allow the matching categories. See our cookie policy.
