Reconstruction of articulated objects from point correspondences in a single uncalibrated image

Exploiting Temporal Context for 3D Human Pose Estimation in the Wild

“…A common approach with the former representation is to "lift" 2D keypoints (either ground truth or from a 2D pose detector) to 3D. This has been recently done with neural networks [28,57,31] and previously using a dictionary of 3D skeletons [38,2,59,54] or other priors [47,50,2] to constrain the problem. The point cloud representation also allows one to train a CNN to regress directly from an image (instead of 2D keypoints) to 3D joints using supervision from motion capture datasets like Human 3.6M [35,41,34].…”

“…A key challenge with 3D pose estimation in-the-wild is the lack of ground truth for people performing arbitrary, unconstrained actions in-the-wild (as typically found on images scraped from the internet). However, a suitable proxy for 3D pose estimation quality is ordinal depth [47,34] i.e. given two keypoints, predict the relative depth ordering by specifying which keypoint is in front of the other.…”

“…given two keypoints, predict the relative depth ordering by specifying which keypoint is in front of the other. This utility of this task was demonstrated by Taylor [47], who showed that the 3D skeleton of a person could be reconstructed perfectly if exact 2D keypoint correspondences, bone lengths and ordinal relations between keypoints were known, assuming an orthographic camera.…”

Garment Modeling from a Single Image

“…Our method firstly utilizes [ZFL * 10, CGZZ] to estimate mannequin 3D pose and shape (Figure 2(b)) from the input image. The 3D pose is recovered by a semi-automatic pose estimation method [Tay00] using the user-specified 2D joints. The recovered 3D orientations and rotations of skeletal bones can be interactively refined by users.…”

“…where L is one point in the oriented facet F li , L li J is the 3D joints for bone l i recovered by the semi-automatic pose estimation method [Tay00], and n li is the normal of the the oriented facet F li . R li is the 3-by-3 rotation matrix of bone l i calculated by using the absolute angles of the recovery pose.…”