Mono-ViFI: A Unified Framework for Self-supervised Monocular Depth Estimation

doi:doi:10.57702/7yg6k69l

Mono-ViFI: A Unified Framework for Self-supervised Monocular Depth Estimation

Self-supervised monocular depth estimation has gathered no-table interest since it can liberate training from dependency on depth annotations. In monocular video training case, recent methods only conduct view synthesis between existing camera views, leading to insuffi-cient guidance. To tackle this, we try to synthesize more virtual camera views by flow-based video frame interpolation (VFI), termed as tempo-ral augmentation.

BibTex:

@dataset{Jinfeng_Liu_and_Lingtong_Kong_and_Bo_Li_and_Zerong_Wang_and_Hong_Gu_and_Jinwei_Chen_2024,
    abstract = {Self-supervised monocular depth estimation has gathered no-table interest since it can liberate training from dependency on depth annotations. In monocular video training case, recent methods only conduct view synthesis between existing camera views, leading to insuffi-cient guidance. To tackle this, we try to synthesize more virtual camera views by flow-based video frame interpolation (VFI), termed as tempo-ral augmentation.},
    author = {Jinfeng Liu and Lingtong Kong and Bo Li and Zerong Wang and Hong Gu and Jinwei Chen},
    doi = {10.57702/7yg6k69l},
    institution = {No Organization},
    keyword = {'data augmentation', 'monocular depth estimation', 'self-supervised learning', 'video frame interpolation'},
    month = {dec},
    publisher = {TIB},
    title = {Mono-ViFI: A Unified Framework for Self-supervised Monocular Depth Estimation},
    url = {https://service.tib.eu/ldmservice/dataset/mono-vifi--a-unified-framework-for-self-supervised-monocular-depth-estimation},
    year = {2024}
}