Conditioning Ground Truth — Mug (512px)
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.
Conditioning maps for guided image generation
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.
44 of 44 files
Conditioning Map — Mug Canny Edges (512px)
Binary Canny edge map extracted from the ground truth — feed as a structure-control input and score the generated result against the reference.
Conditioning Map — Mug Depth Map (512px)
Synthetic depth map (near = bright) for depth-conditioned generation and monocular depth-estimation regression against a known reference.
Conditioning Map — Mug Normal Map (512px)
Tangent-space surface-normal map encoded from the scene depth — a normal-conditioning input for guided generation and relighting tests.
Conditioning Map — Mug Segmentation Map (512px)
Semantic segmentation map (subject vs background) — the label reference for segmentation-conditioned generation and mask-quality scoring.
Conditioning Map — Mug Scribble (512px)
Sparse scribble derived from the edges — the loose hand-drawn control input for scribble-guided image generation.
Conditioning Map — Mug Line Art (512px)
Clean line-art extraction (black lines on white) for line-art-conditioned generation and line-extraction quality tests.
Conditioning Ground Truth — Apple (512px)
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.
Conditioning Map — Apple Canny Edges (512px)
Binary Canny edge map extracted from the ground truth — feed as a structure-control input and score the generated result against the reference.
Conditioning Map — Apple Depth Map (512px)
Synthetic depth map (near = bright) for depth-conditioned generation and monocular depth-estimation regression against a known reference.
Conditioning Map — Apple Normal Map (512px)
Tangent-space surface-normal map encoded from the scene depth — a normal-conditioning input for guided generation and relighting tests.
Conditioning Map — Apple Segmentation Map (512px)
Semantic segmentation map (subject vs background) — the label reference for segmentation-conditioned generation and mask-quality scoring.
Conditioning Map — Apple Scribble (512px)
Sparse scribble derived from the edges — the loose hand-drawn control input for scribble-guided image generation.
Conditioning Map — Apple Line Art (512px)
Clean line-art extraction (black lines on white) for line-art-conditioned generation and line-extraction quality tests.
Conditioning Ground Truth — Plant (512px)
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.
Conditioning Map — Plant Canny Edges (512px)
Binary Canny edge map extracted from the ground truth — feed as a structure-control input and score the generated result against the reference.
Conditioning Map — Plant Depth Map (512px)
Synthetic depth map (near = bright) for depth-conditioned generation and monocular depth-estimation regression against a known reference.
Conditioning Map — Plant Normal Map (512px)
Tangent-space surface-normal map encoded from the scene depth — a normal-conditioning input for guided generation and relighting tests.
Conditioning Map — Plant Segmentation Map (512px)
Semantic segmentation map (subject vs background) — the label reference for segmentation-conditioned generation and mask-quality scoring.
Conditioning Map — Plant Scribble (512px)
Sparse scribble derived from the edges — the loose hand-drawn control input for scribble-guided image generation.
Conditioning Map — Plant Line Art (512px)
Clean line-art extraction (black lines on white) for line-art-conditioned generation and line-extraction quality tests.
Conditioning Ground Truth — Robot (512px)
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.
Conditioning Map — Robot Canny Edges (512px)
Binary Canny edge map extracted from the ground truth — feed as a structure-control input and score the generated result against the reference.
Conditioning Map — Robot Depth Map (512px)
Synthetic depth map (near = bright) for depth-conditioned generation and monocular depth-estimation regression against a known reference.
Conditioning Map — Robot Normal Map (512px)
Tangent-space surface-normal map encoded from the scene depth — a normal-conditioning input for guided generation and relighting tests.
Conditioning Map — Robot Segmentation Map (512px)
Semantic segmentation map (subject vs background) — the label reference for segmentation-conditioned generation and mask-quality scoring.
Conditioning Map — Robot Scribble (512px)
Sparse scribble derived from the edges — the loose hand-drawn control input for scribble-guided image generation.
Conditioning Map — Robot Line Art (512px)
Clean line-art extraction (black lines on white) for line-art-conditioned generation and line-extraction quality tests.
Conditioning Map — Robot Pose Skeleton (512px)
OpenPose-style keypoint skeleton for the figure — a pose-control input for guided generation and a target for pose-estimation checks.
Conditioning Ground Truth — Cat (512px)
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.
Conditioning Map — Cat Canny Edges (512px)
Binary Canny edge map extracted from the ground truth — feed as a structure-control input and score the generated result against the reference.
Conditioning Map — Cat Depth Map (512px)
Synthetic depth map (near = bright) for depth-conditioned generation and monocular depth-estimation regression against a known reference.
Conditioning Map — Cat Normal Map (512px)
Tangent-space surface-normal map encoded from the scene depth — a normal-conditioning input for guided generation and relighting tests.
Conditioning Map — Cat Segmentation Map (512px)
Semantic segmentation map (subject vs background) — the label reference for segmentation-conditioned generation and mask-quality scoring.
Conditioning Map — Cat Scribble (512px)
Sparse scribble derived from the edges — the loose hand-drawn control input for scribble-guided image generation.
Conditioning Map — Cat Line Art (512px)
Clean line-art extraction (black lines on white) for line-art-conditioned generation and line-extraction quality tests.
Conditioning Map — Cat Pose Skeleton (512px)
OpenPose-style keypoint skeleton for the figure — a pose-control input for guided generation and a target for pose-estimation checks.
Conditioning Ground Truth — Fruit (512px)
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.
Conditioning Map — Fruit Canny Edges (512px)
Binary Canny edge map extracted from the ground truth — feed as a structure-control input and score the generated result against the reference.
Conditioning Map — Fruit Depth Map (512px)
Synthetic depth map (near = bright) for depth-conditioned generation and monocular depth-estimation regression against a known reference.
Conditioning Map — Fruit Normal Map (512px)
Tangent-space surface-normal map encoded from the scene depth — a normal-conditioning input for guided generation and relighting tests.
Conditioning Map — Fruit Segmentation Map (512px)
Semantic segmentation map (subject vs background) — the label reference for segmentation-conditioned generation and mask-quality scoring.
Conditioning Map — Fruit Scribble (512px)
Sparse scribble derived from the edges — the loose hand-drawn control input for scribble-guided image generation.
Conditioning Map — Fruit Line Art (512px)
Clean line-art extraction (black lines on white) for line-art-conditioned generation and line-extraction quality tests.