We tackle the tasks of: 1) predicting a Canonical Surface Map** (CSM) that indicates the
map** from 2D pixels to corresponding points on a canonical template shape, and 2) …

In this work, we focus on the task of learning and representing dense correspondences in
deformable object categories. While this problem has been considered before, solutions so …

Modeling hand-object manipulations is essential for understanding how humans interact
with their environment. While of practical importance, estimating the pose of hands and …

Though much progress has been achieved in single-image 3D human recovery, estimating
3D model for in-the-wild images remains a formidable challenge. The reason lies in the fact …

Recent contributions have demonstrated that it is possible to recognize the pose of humans
densely and accurately given a large dataset of poses annotated in detail. In principle, the …

Clothes undergo complex geometric deformations, which lead to appearance changes. To
edit human videos in a physically plausible way, a texture map must take into account not …

Video action detectors are usually trained using datasets with fully-supervised temporal
annotations. Building such datasets is an expensive task. To alleviate this problem, recent …

With a proliferation of generic domain-adaptation approaches, we report a simple yet
effective technique for learning difficult per-pixel 2.5 D and 3D regression representations of …

Human densepose estimation, aiming at establishing dense correspondences between 2D
pixels of human body and 3D human body template, is a key technique in enabling …

Recovering dense human poses from images plays a critical role in establishing an image-
to-surface correspondence between RGB images and the 3D surface of the human body …