Severalworksextend thesetodynamic scenes captured with monocular video, with promising performance.

Neural Information Processing Systems http://nips.cc/

Following the unsupervised literature [4, 3, 5], the siamese networkFθ is trained by imposing structural properties on the fmapC such as bijectivity and orthogonality on the shape pairs in the training set.

Instead of learning a radiance field with a uniform occupancy prior, we constrain it by a structured implicit human body model, represented using signed distance functions.

MLPs with"noencoding" struggle tofit high frequencysegments (see appendix for train details). Our workenables MLP networks toadaptivelyfitavarying spectrum offine details that previous methods struggle to capture in a single shot, without involved tuning of parameters or domain specific preprocessing.

Applying image processing algorithms independently toeachvideo frame often leads to temporal inconsistencyin the resulting video.