In this work, we focus on synthesizing high-fidelity novel view images for arbitrary human
performers, given a set of sparse multi-view images. It is a challenging task due to the large …

Hand-object interaction understanding and the barely addressed novel view synthesis are
highly desired in the immersive communication, whereas it is challenging due to the high …

The various aspects like modeling and interpreting 3D environments and surroundings have
enticed humans to progress their research in 3D Computer Vision, Computer Graphics, and …

In this article, we introduce Neural-ABC, a novel parametric model based on neural implicit
functions that can represent clothed human bodies with disentangled latent spaces for …

Reconstructing general dynamic scenes is important for many computer vision and graphics
applications. Recent works represent the dynamic scene with neural radiance fields for …

Abstract 3D human avatar reconstruction aims to reconstruct the 3D geometric shape and
appearance of the human body from various data inputs, such as images, videos, and depth …

In today's digital realm, where the metaverse, virtual reality, and video games converge, the
importance of 3D human body reconstruction methods is undeniable. These techniques are …

This paper presents InceptionHuman, a prompt-to-NeRF framework that allows easy control
via a combination of prompts in different modalities (eg, text, poses, edge, segmentation …

We investigate the problem of efficient reconstruction and modeling of clothed human
avatars from sparse multi-view and monocular videos. Existing state-of-the-art methods are …