You're currently viewing an old version of this dataset. To see the current version, click here.

COCO dataset

Text-to-image synthesis has achieved high-quality results with recent advances in diffusion models. However, text input alone has high spatial ambiguity and limited user controllability. Most existing methods allow spatial control through additional visual guidance (e.g., sketches and semantic masks) but require additional training with annotated images.

Data and Resources

Cite this as

Yuki Endo (2024). Dataset: COCO dataset. https://doi.org/10.57702/h82873pp

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2302.08113
Citation
  • https://doi.org/10.1109/CVPR52688.2022.00303
  • https://doi.org/10.48550/arXiv.2004.05746
  • https://doi.org/10.48550/arXiv.2402.08657
  • https://doi.org/10.48550/arXiv.1904.13273
  • https://doi.org/10.48550/arXiv.1703.06953
  • https://doi.org/10.48550/arXiv.2401.01732
  • https://doi.org/10.48550/arXiv.2007.14110
  • https://doi.org/10.48550/arXiv.2104.13602
  • https://doi.org/10.48550/arXiv.1908.07323
  • https://doi.org/10.48550/arXiv.1803.08225
  • https://doi.org/10.48550/arXiv.1809.09607
  • https://doi.org/10.48550/arXiv.2312.04113
  • https://doi.org/10.48550/arXiv.1705.07206
  • https://doi.org/10.48550/arXiv.2209.12744
  • https://doi.org/10.48550/arXiv.2402.14017
  • https://doi.org/10.48550/arXiv.2308.06027
  • https://doi.org/10.48550/arXiv.2105.11095
  • https://doi.org/10.48550/arXiv.2306.17074
  • https://doi.org/10.48550/arXiv.2401.10227
Author Yuki Endo
Homepage https://cocodataset.org/