Single reference
Unicolor
Paper: https://arxiv.org/abs/2209.11223
This model generates diverse results where the color is not constrained by the reference image.
Task | Image #1 | Image #2 | Image #3 | Image #4 |
---|---|---|---|---|
Recolor source | ||||
Inverted reference | ||||
Task | Image #1 | Image #2 | Image #3 | Reference |
Full correspondence | ||||
Full correspondence | ||||
Partial reference | ||||
Partial reference | ||||
Partial source | ||||
Partial source | ||||
Semantic correspondence strong | ||||
Semantic correspondence strong | ||||
Semantic correspondence weak | ||||
Semantic correspondence weak | ||||
Distractors | ||||
Random noise | ||||
Random noise | ||||
Gray | ||||
Gray | ||||
Contemporary | ||||
Contemporary | ||||
Contemporary |
Additional Information
- Last updated: 11 April 2024 10:48
- GPU info: NVIDIA GeForce GTX 1080 Ti 11 GB, Compute Capability 6.1
- CUDA version: 11.8
- PyTorch version: 2.2.1