Recent hand-object interaction datasets show limited real object variabi...
Scene coordinates regression (SCR), i.e., predicting 3D coordinates for ...
Despite impressive performance for high-level downstream tasks,
self-sup...
Robots with multi-fingered grippers could perform advanced manipulation ...
Masked Image Modeling (MIM) has recently been established as a potent
pr...
Training state-of-the-art models for human pose estimation in videos req...
Training state-of-the-art models for human body pose and shape recovery ...
Many problems in machine learning involve regressing outputs that do not...
Predicting 3D human pose from images has seen great recent improvements....
We introduce DOPE, the first method to detect and estimate whole-body 3D...
In this work, we study how well different type of approaches generalise ...
While 3D object detection and pose estimation has been studied for a lon...
With more and more household objects built on planned obsolescence and
c...
The pose of a rigid object is usually regarded as a rigid transformation...