|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Although current approaches have demonstrated the potential in real world settings, they still fail to produce reconstructions with the level of detail often present in the input images.
Human motion is fundamental to understanding behavior.
Ranked #6 on 3D Human Pose Estimation on 3DPW (using extra training data)
We introduce Pixel-aligned Implicit Function (PIFu), a highly effective implicit representation that locally aligns pixels of 2D images with the global context of their corresponding 3D object.
We study 3D shape modeling from a single image and make contributions to it in three aspects.
Ranked #1 on 3D Shape Classification on Pix3D
Through our investigation, we found that such a pre-trained GAN indeed contains rich 3D knowledge and thus can be used to recover 3D shape from a single 2D image in an unsupervised manner.
While the low-frequency component is predicted from pose, shape and style parameters with an MLP, the high-frequency component is predicted with a mixture of shape-style specific pose models.
We present Multi-Garment Network (MGN), a method to predict body shape and clothing, layered on top of the SMPL model from a few frames (1-8) of a video.
To solve this, we propose Implicit Feature Networks (IF-Nets), which deliver continuous outputs, can handle multiple topologies, and complete shapes for missing or sparse input data retaining the nice properties of recent learned implicit functions, but critically they can also retain detail when it is present in the input data, and can reconstruct articulated humans.
We present a method that infers spatial arrangements and shapes of humans and objects in a globally consistent 3D scene, all from a single image in-the-wild captured in an uncontrolled environment.