ConsID-Gen Dataset

ConsIDVid Summary This dataset is released with our paper: ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video GenerationMingyang Wu, Ashirbad Mishra, Soumik Dey, Shuo Xing, Naveen Ravipati, Hansi Wu, Binbin Li, Zhengzhong Tu (2026) Accepted by CVPR 2026 This release contains processed videos and hierarchical captions used in ConsID-Gen experiments across: public synthesis (MVImgNet) public (CO3D, OmniObject3D, Objectron) The dataset is designed… See the full description on the dataset page:

Source: Hugging Face Hub (mingyang-wu/ConsIDVid). Metadata imported from the dataset’s Hub tags.