Detailed Human Avatars from Monocular Video

08/03/2018
by   Thiemo Alldieck, et al.
4

We present a novel method for high detail-preserving human avatar creation from monocular video. A parameterized body model is refined and optimized to maximally resemble subjects from a video showing them from all sides. Our avatars feature a natural face, hairstyle, clothes with garment wrinkles, and high-resolution texture. Our paper contributes facial landmark and shading-based human body shape refinement, a semantic texture prior, and a novel texture stitching strategy, resulting in the most sophisticated-looking human avatars obtained from a single video to date. Numerous results show the robustness and versatility of our method. A user study illustrates its superiority over the state-of-the-art in terms of identity preservation, level of detail, realism, and overall user preference.

READ FULL TEXT

page 1

page 5

page 6

page 7

page 8

research
04/19/2021

Temporal Consistency Loss for High Resolution Textured and Clothed 3DHuman Reconstruction from Monocular Video

We present a novel method to learn temporally consistent 3D reconstructi...
research
03/17/2023

MoRF: Mobile Realistic Fullbody Avatars from a Monocular Video

We present a new approach for learning Mobile Realistic Fullbody (MoRF) ...
research
03/13/2018

Video Based Reconstruction of 3D People Models

This paper describes how to obtain accurate 3D body models and texture o...
research
04/18/2019

Tex2Shape: Detailed Full Human Body Geometry from a Single Image

We present a simple yet effective method to infer detailed full human bo...
research
11/29/2021

Human Performance Capture from Monocular Video in the Wild

Capturing the dynamically deforming 3D shape of clothed human is essenti...
research
12/02/2016

Photorealistic Facial Texture Inference Using Deep Neural Networks

We present a data-driven inference method that can synthesize a photorea...

Please sign up or login with your details

Forgot password? Click here to reset