ICON

Overview

Current methods for learning realistic and animatable 3D clothed avatars need either posed 3D scans or 2D images with carefully controlled user poses. In contrast, our goal is to learn the avatar from only 2D images of people in unconstrained poses. Given a set of images, our method estimates a detailed 3D surface from each image and then combines these into an animatable avatar. Implicit functions are well suited to the first task, as they can capture details like hair or clothes. Current methods, however, are not robust to varied human poses and often produce 3D surfaces with broken or disembodied limbs, missing details, or non-human shapes. The problem is that these methods use global feature encoders that are sensitive to global pose. To address this, we propose ICON ("Implicit Clothed humans Obtained from Normals"), which uses local features, instead. ICON has two main modules, both of which exploit the SMPL(-X) body model. First, ICON infers detailed clothed-human normals (front/back) conditioned on the SMPL(-X) normals. Second, a visibility-aware implicit surface regressor produces an iso-surface of a human occupancy field. Importantly, at inference time, a feedback loop alternates between refining the SMPL(-X) mesh using the inferred clothed normals and then refining the normals. Given multiple reconstructed frames of a subject in varied poses, we use SCANimate to produce an animatable avatar from them. Evaluation on the AGORA and CAPE datasets shows that ICON outperforms the state of the art in reconstruction, even with heavily limited training data. Additionally, it is much more robust to out-of-distribution samples, e.g., in-the-wild poses/images and out-of-frame cropping. ICON takes a step towards robust 3D clothed human reconstruction from in-the-wild images. This enables creating avatars directly from video with personalized and natural pose-dependent cloth deformation.

Main Contributions

Body-Guided Normal Prediction & Local-feature based implicit 3D reconstruction

ICON takes, as input, an RGB image of a segmented clothed human and a SMPL body estimated from the image. The SMPL body is used to guide two of ICON’s modules: one infers detailed clothed-human surface normals (front and back views), and the other infers a visibility-aware implicit surface (iso-surface of an occupancy field).

SMPL refinement in a feedback loop

Errors in the initial SMPL estimate, however, might misguide inference. Thus, at inference time, an iterative feedback loop refines SMPL (i.e. its 3D shape, pose and translation) using the inferred detailed normals, and vice versa, leading to a refined implicit shape with better 3D details.

Acknowlegments

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No.860768 (CLIPE Project)

Disclosure

MJB has received research gift funds from Adobe, Intel, Nvidia, Meta/Facebook, and Amazon. MJB has financial interests in Amazon, Datagen Technologies, and Meshcapade GmbH. While MJB was a part-time employee of Amazon during this project, his research was performed solely at, and funded solely by, the Max Planck Society.

Bibtex

@inproceedings{xiu2022icon,
title = {{ICON}: {I}mplicit {C}lothed humans {O}btained from {N}ormals},
author = {Xiu, Yuliang and Yang, Jinlong and Tzionas, Dimitrios and Black, Michael J.},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2022},
pages = {13296-13306}
}

ICON: Implicit Clothed humans Obtained from Normals

Paper

Code

Keynote

Poster

Colab

HuggingFace

Introduction Video

Interactive Demo from HuggingFace Space

Overview

Paper

Code

Colab

Main Contributions

Qualitative Results (Only Geometry)

Application: create an animatable avatar from 400 images

Human Digitization with Implicit Representation

Acknowlegments

Disclosure

Bibtex

Contact