HUMBI: A Large Multiview Dataset of Human Body Expressions

Abstract: 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 gaze, face, hand, body, and garment from assorted people. 107 synchronized HD cam- eras are used to capture 772 distinctive subjects across gen- der, ethnicity, age, and physical condition. With the mul- tiview image streams, we reconstruct high fidelity body ex- pressions using 3D mesh models, which allows representing view-specific appearance using their canonical atlas. We demonstrate that HUMBI is highly effective in learning and reconstructing a complete human model and is complemen- tary 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.

14/06/2020

Renat Bashirov, Anastasia Ianina, Karim Iskakov and
Yevgeniy Kononenko, Valeriya Strizhkova, Victor Lempitsky, Alexander Vakhitov

Ruilong Li, Karl Bladin, Yajie Zhao and
Chinmay Chinara, Owen Ingraham, Pengda Xiang, Xinglei Ren, Pratusha Prasad, Bipin Kishore, Jun Xing, Hao Li

Keywords Paper

deep, 3d, morphable, face, model, human, style, gan, albedo, pbr

1:01

06/12/2021

Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction

structured representation, 3D representation, 3D Gaussians, image generation, image synthesis, image editing, controlled generation, GANs

2:49

06/12/2020

Martin Rünz, Kejie Li, Meng Tang and
Lingni Ma, Chen Kong, Tanner Schmidt, Ian Reid, Lourdes Agapito, Julian Straub, Steven Lovegrove, Richard Newcombe

Keywords Paper

reconstruction, shape embedding, 3d vision, object detection, shape prior, object representation, monocular, sdf, pointcloud, inference

1:01

06/12/2021

Haoyu Ma, Liangjian Chen, Deying Kong and
Zhe Wang, Xingwei Liu, Hao Tang, Xiangyi Yan, Yusheng Xie, Shih-Yao Lin, Xiaohui Xie

image synthesis, pose transfer, generative adversarial networks, image editing, attribute separation, feature disentanglement, fashion ai

4:56

22/11/2021

deblurring, face, multi-view, video, blur, GAN, novel view synthesis, inversion, deep learning, dataset

2:50

06/07/2020

Representation Learning, Self-supervised Learning, Unsupervised 3D Pose Estimation, View-Invariant Pose Estimation, View-Invariant Action Recognition, View-Invariant Action Assessment, View-Invariant Human Movemnet Assessment, Human Posture Representation, Unsupervised Action Recognition, Unsupervised Action Assessment

2:59

14/06/2020

face reenactment, triplet perceptual loss, generative adversarial network, facial expression transformation, disentanglement of appearance and geometry information

1:01

02/02/2021

3d scene recomposition, 3d scene reconstruction, deep reinforcement learning, learning-based icp (licp), 3d geometry learning, 3d cad models, 3d shapes, room layout estimation, 3d geometry deep network, iterative closest point

1:01

14/06/2020

3d flow, dense 3d facial motion capture, optical flow, scene flow, 3d reconstruction and tracking, in-the-wild monocular tracking, facial reenactment, expression recognition, performance capture, non-rigid facial deformations

1:01

16/11/2020

3d face dataset, face prediction, riggable model, 3d morphable model, dynamic details, deep neural network, displacement map

1:00

30/11/2020