3D Human Reconstruction in the Wild with Synthetic Data Using Generative Models

17 Mar 2024  ·  Yongtao Ge, Wenjia Wang, Yongfan Chen, Hao Chen, Chunhua Shen ·

In this work, we show that synthetic data created by generative models is complementary to computer graphics (CG) rendered data for achieving remarkable generalization performance on diverse real-world scenes for 3D human pose and shape estimation (HPS). Specifically, we propose an effective approach based on recent diffusion models, termed HumanWild, which can effortlessly generate human images and corresponding 3D mesh annotations. We first collect a large-scale human-centric dataset with comprehensive annotations, e.g., text captions and surface normal images. Then, we train a customized ControlNet model upon this dataset to generate diverse human images and initial ground-truth labels. At the core of this step is that we can easily obtain numerous surface normal images from a 3D human parametric model, e.g., SMPL-X, by rendering the 3D mesh onto the image plane. As there exists inevitable noise in the initial labels, we then apply an off-the-shelf foundation segmentation model, i.e., SAM, to filter negative data samples. Our data generation pipeline is flexible and customizable to facilitate different real-world tasks, e.g., ego-centric scenes and perspective-distortion scenes. The generated dataset comprises 0.79M images with corresponding 3D annotations, covering versatile viewpoints, scenes, and human identities. We train various HPS regressors on top of the generated data and evaluate them on a wide range of benchmarks (3DPW, RICH, EgoBody, AGORA, SSP-3D) to verify the effectiveness of the generated data. By exclusively employing generative models, we generate large-scale in-the-wild human images and high-quality annotations, eliminating the need for real-world data collection.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Human Pose Estimation 3DPW CLIFF (3DPW+HumanWild+BEDLAM+AGORA) PA-MPJPE 41.9 # 21
MPJPE 65.2 # 11
MPVPE 76.8 # 10
3D Human Pose Estimation 3DPW CLIFF PA-MPJPE 52.7 # 79
MPJPE 87.3 # 91
MPVPE 102.1 # 65

Methods