Independent publisher
PeiyuZhuang
PatrickZZZ
Models in Library0
Datasets in Library2
Models on Hugging Face1
Followers—
Compare the published evidence
This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Image to image.
Reported licenses: other. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Datasets
PAPE PAPE (Plausible Anomalous Paired Edits) is a paired image-editing dataset for localizing semantic edits. Each sample edits one object in a real photograph twice: a semantically ordinary replacement, and a replacement that introduces one controlled semantic anomaly. Both edits have a binary change mask. Only pairs whose normal and abnormal masks have IoU of at least 0.5 are included. Source photographs come from COCO, ImageNet, and Places. Those photographs stay under the