COCO-stuff

COCO-Stuff augments all 164K images of the popular COCO dataset with pixel-level stuff annotations. These annotations can be used for scene understanding tasks like semantic segmentation, object detection and image captioning.

Papers using COCO-stuff (6)

Heterogeneous Image GNN: Graph-Conditioned Diffusion for Image Synthesis2025Joint Generative Modeling of Grounded Scene Graphs and Images via Diffusion Models2024Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis2020 · 19 citesLayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation2023 · 8 citesUnifying conditional and unconditional semantic image synthesis with OCO-GAN2022Unlocking Pre-trained Image Backbones for Semantic Image Synthesis2023