3D Clothed Human Reconstruction in the Wild
Gyeongsik Moon, Hyeongjin Nam, Takaaki Shiratori, Kyoung Mu Lee

TL;DR
ClothWild is a novel framework for 3D clothed human reconstruction from in-the-wild images, using weak supervision and DensePose-based loss to improve robustness and accuracy over existing methods.
Contribution
The paper introduces ClothWild, a weakly supervised approach with DensePose loss to enhance 3D human reconstruction in diverse, real-world images.
Findings
Outperforms state-of-the-art methods on public in-the-wild datasets.
Demonstrates robustness to diverse poses and appearances.
Achieves more accurate reconstructions with weak supervision.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Pose and Action Recognition · 3D Shape Modeling and Analysis · Generative Adversarial Networks and Image Synthesis
