C3DPO: Canonical 3D pose networks for non-rigid structure from motion

We propose C3DPO, a method for extracting 3D models of deformable objects from 2D keypoint annotations in unconstrained images. We do so by learning a deep network that reconstructs a 3D object from a single view at a time, accounting for partial occlusions, and explicitly factoring the effects of v...

Mô tả đầy đủ

Chi tiết về thư mục
Những tác giả chính: Novotny, D, Ravi, N, Graham, B, Neverova, N, Vedaldi, A
Định dạng: Conference item
Được phát hành: 2020

Những quyển sách tương tự