HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challenge

2021-09-30 · Jae Shin Yoon, Zhixuan Yu, Jaesik Park, Hyun Soo Park

This paper presents a new large multiview dataset called HUMBI for human body expressions with natural clothing. The goal of HUMBI is to facilitate modeling view-specific appearance and geometry of five primary body signals including gaze, face, hand, body, and garment from assorted people. 107 synchronized HD cameras are used to capture 772 distinctive subjects across gender, ethnicity, age, and style. With the multiview image streams, we reconstruct high fidelity body expressions using 3D mesh models, which allows representing view-specific appearance. We demonstrate that HUMBI is highly effective in learning and reconstructing a complete human model and is complementary to the existing datasets of human body expressions with limited views and subjects such as MPII-Gaze, Multi-PIE, Human3.6M, and Panoptic Studio datasets. Based on HUMBI, we formulate a new benchmark challenge of a pose-guided appearance rendering task that aims to substantially extend photorealism in modeling diverse human expressions in 3D, which is the key enabling factor of authentic social tele-presence. HUMBI is publicly available at http://humbi-data.net

📄 PDF Abstract BibTeX arXiv:2110.00119

Code (0)

등록된 구현이 없습니다.

HUMBI: A Large Multiview Dataset of Human Body Expressions

2018-12-01 · CVPR 2020 6 · Zhixuan Yu, Jae Shin Yoon, In Kyu Lee, Prashanth Venkatesh 외

BAG: Body-Aligned 3D Wearable Asset Generation

2025-01-27 · Zhongjin Luo, Yang Li, Mingrui Zhang, Senbo Wang 외

While recent advancements have shown remarkable progress in general 3D shape generation models, the challenge of leveraging these approaches to automatically generate wearable 3D assets remains unexplored. To this end, w…

3D Generation 3D Shape Generation Diversity

Multiple human 3d pose estimation from multiview images

2017-09-04 · Sara Ershadi-Nasab, Erfan Noury, Shohreh Kasaei, Esmaeil Sanaei

Multiple human 3D pose estimation is a challenging task. It is mainly because of large variations in the scale and pose of humans, fast motions, multiple persons in the scene, and arbitrary number of visible body parts d…

3D Multi-Person Pose Estimation 3D Pose Estimation Pose Estimation

Multi-view Human Body Mesh Translator

2022-10-04 · Xiangjian Jiang, Xuecheng Nie, Zitian Wang, Luoqi Liu 외

Existing methods for human mesh recovery mainly focus on single-view frameworks, but they often fail to produce accurate results due to the ill-posed setup. Considering the maturity of the multi-view motion capture syste…

Human Mesh Recovery

PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing

2025-01-01 · CVPR 2025 1 · Peng Li, Wangguandong Zheng, YuAn Liu, Tao Yu 외

Photorealistic 3D human modeling is essential for various applications and has seen tremendous progress. However, existing methods for monocular full-body reconstruction, typically relying on front and/or predicted b…

3D Human Reconstruction Anatomy