SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.10053 · ECCV · 2022

3D Clothed Human Reconstruction in the Wild

Kyoung Lee, Hyeongjin Nam, Gyeongsik Moon, Takaaki Shiratori

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Although much progress has been made in 3D clothed human reconstruction, most of the existing methods fail to produce robust results from in-the-wild images, which contain diverse human poses and appearances. This is mainly due to the large domain gap between training datasets and in-the-wild datasets. The training datasets are usually synthetic ones, which contain rendered images from GT 3D scans. However, such datasets contain simple human poses and less natural image appearances compared to those of real in-the-wild datasets, which makes generalization of it to in-the-wild images extremely challenging. To resolve this issue, in this work, we propose ClothWild, a 3D clothed human reconstruction framework that firstly addresses the robustness on in-thewild images. First, for the robustness to the domain gap, we propose a weakly supervised pipeline that is trainable with 2D supervision targets of in-the-wild datasets. Second, we design a DensePose-based loss function to reduce ambiguities of the weak supervision. Extensive empirical tests on several public in-the-wild datasets demonstrate that our proposed ClothWild produces much more accurate and robust results than the state-of-the-art methods. The codes are available in here. This work was primarily done while Gyeongsik Moon was in SNU. BCNet ClothWild (Ours) input image in-the-wild images

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2207.10053")
get_code_for_paper("2207.10053")
have("2207.10053")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2207.10053.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2207.10053.svg)](https://syntology.ai/paper/2207.10053)

Connect an agent — have() is free.