InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds

12/20/2022
by   Tianjian Jiang, et al.
0

In this paper, we take a significant step towards real-world applicability of monocular neural avatar reconstruction by contributing InstantAvatar, a system that can reconstruct human avatars from a monocular video within seconds, and these avatars can be animated and rendered at an interactive rate. To achieve this efficiency we propose a carefully designed and engineered system, that leverages emerging acceleration structures for neural fields, in combination with an efficient empty space-skipping strategy for dynamic scenes. We also contribute an efficient implementation that we will make available for research purposes. Compared to existing methods, InstantAvatar converges 130x faster and can be trained in minutes instead of hours. It achieves comparable or even better reconstruction quality and novel pose synthesis results. When given the same time budget, our method significantly outperforms SoTA methods. InstantAvatar can yield acceptable visual quality in as little as 10 seconds training time.

READ FULL TEXT

page 1

page 6

page 7

page 8

research
10/04/2022

SelfNeRF: Fast Training NeRF for Human from Monocular Self-rotating Video

In this paper, we propose SelfNeRF, an efficient neural radiance field b...
research
12/02/2022

Fast Non-Rigid Radiance Fields from Monocularized Data

3D reconstruction and novel view synthesis of dynamic scenes from collec...
research
09/20/2022

wildNeRF: Complete view synthesis of in-the-wild dynamic scenes captured using sparse monocular data

We present a novel neural radiance model that is trainable in a self-sup...
research
04/20/2023

Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion

We present Farm3D, a method to learn category-specific 3D reconstructors...
research
06/05/2022

FOF: Learning Fourier Occupancy Field for Monocular Real-time Human Reconstruction

The advent of deep learning has led to significant progress in monocular...
research
06/29/2023

PVP: Personalized Video Prior for Editable Dynamic Portraits using StyleGAN

Portrait synthesis creates realistic digital avatars which enable users ...
research
11/25/2021

VaxNeRF: Revisiting the Classic for Voxel-Accelerated Neural Radiance Field

Neural Radiance Field (NeRF) is a popular method in data-driven 3D recon...

Please sign up or login with your details

Forgot password? Click here to reset