Garment4D: Garment Reconstruction from Point Cloud Sequences

by   Fangzhou Hong, et al.

Learning to reconstruct 3D garments is important for dressing 3D human bodies of different shapes in different poses. Previous works typically rely on 2D images as input, which however suffer from the scale and pose ambiguities. To circumvent the problems caused by 2D images, we propose a principled framework, Garment4D, that uses 3D point cloud sequences of dressed humans for garment reconstruction. Garment4D has three dedicated steps: sequential garments registration, canonical garment estimation, and posed garment reconstruction. The main challenges are two-fold: 1) effective 3D feature learning for fine details, and 2) capture of garment dynamics caused by the interaction between garments and the human body, especially for loose garments like skirts. To unravel these problems, we introduce a novel Proposal-Guided Hierarchical Feature Network and Iterative Graph Convolution Network, which integrate both high-level semantic features and low-level geometric features for fine details reconstruction. Furthermore, we propose a Temporal Transformer for smooth garment motions capture. Unlike non-parametric methods, the reconstructed garment meshes by our method are separable from the human body and have strong interpretability, which is desirable for downstream tasks. As the first attempt at this task, high-quality reconstruction results are qualitatively and quantitatively illustrated through extensive experiments. Codes are available at


page 3

page 4

page 6

page 7

page 9


Masked Surfel Prediction for Self-Supervised Point Cloud Learning

Masked auto-encoding is a popular and effective self-supervised learning...

Ponder: Point Cloud Pre-training via Neural Rendering

We propose a novel approach to self-supervised learning of point cloud r...

Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable Pooling

Existing point cloud feature learning networks often incorporate sequenc...

SHERF: Generalizable Human NeRF from a Single Image

Existing Human NeRF methods for reconstructing 3D humans typically rely ...

Tensorformer: Normalized Matrix Attention Transformer for High-quality Point Cloud Reconstruction

Surface reconstruction from raw point clouds has been studied for decade...

SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration

Extracting robust and general 3D local features is key to downstream tas...

High-Resolution Cranial Defect Reconstruction by Iterative, Low-Resolution, Point Cloud Completion Transformers

Each year thousands of people suffer from various types of cranial injur...

Please sign up or login with your details

Forgot password? Click here to reset