Science

Meshcapade takes the scientific understanding of human body and brings it to you using patented technology.

Want to join our research team? Look at our open positions.

Our Publications

Token HMR Cover

TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation

CVPR 2024

Other selected publications by Meshcapade scientists

Naureen Mahmood

SMPL: A skinned multi-person linear model

M Loper, N Mahmood, J Romero, G Pons-Moll, MJ Black

ACM transactions on graphics (TOG) 34 (6), 1-16, 2015

Learning from synthetic humans

G Varol, J Romero, X Martin, N Mahmood, MJ Black, I Laptev, C Schmid

CVPR 2017

MoSh: Motion and shape capture from sparse markers

M Loper, N Mahmood, MJ Black

ACM Transactions on Graphics (TOG) 33 (6), 1-13, 2014

Dyna: A model of dynamic human shape in motion

G Pons-Moll, J Romero, N Mahmood, MJ Black

ACM Transactions on Graphics (TOG) 34 (4), 1-14, 2015

Muhammed Kocabas

HUGS: Human gaussian splats

M Kocabas, JHR Chang, J Gabriel, O Tuzel, A Ranjan

CVPR 2024

ARCTIC: A dataset for dexterous bimanual hand-object manipulation

Z Fan, O Taheri, D Tzionas, M Kocabas, M Kaufmann, MJ Black, ...

CVPR 2023

SPEC: Seeing people in the wild with an estimated camera

M Kocabas, CHP Huang, J Tesch, L Müller, O Hilliges, MJ Black

CVPR 2021

PARE: Part attention regressor for 3d human body estimation

M Kocabas, CHP Huang, O Hilliges, MJ Black

CVPR 2021

VIBE: Video inference for human body pose and shape estimation

M Kocabas, N Athanasiou, MJ Black

CVPR 2020

Yu Sun

TRACE: 5D Temporal Regression of Avatars With Dynamic Cameras in 3D Environments

Y. Sun, Q. Bao, W. Liu, T. Mei, M. J. Black

CVPR 2023

Putting People in their Place: Monocular Regression of 3D People in Depth

Y. Sun, W. Liu, Q. Bao, Y. Fu, T. Mei, M. J. Black

CVPR 2022

Monocular, One-Stage, Regression of Multiple 3D People

Y. Sun, Q. Bao, W. Liu, Y. Fu, M. J. Black, T. Mei

CVPR 2021

Yan Zhang

Generating 3d people in scenes without people

Y Zhang, M Hassan, H Neumann, MJ Black, S Tang

CVPR 2020

LEAP: Learning articulated occupancy of people

M Mihajlovic, Y Zhang, MJ Black, S Tang

CVPR 2021

We are more than our joints: Predicting how 3d bodies move

Y Zhang, MJ Black, S Tang

CVPR 2021

We are more than our joints: Predicting how 3d bodies move

Y Zhang, MJ Black, S Tang

CVPR 2023

The wanderings of odysseus in 3d scenes

Y Zhang, S Tang

CVPR 2022

Yao Feng

Learning an animatable detailed 3D face model from in-the-wild images

Y Feng, H Feng, MJ Black, T Bolkart

SIGGRAPH 2021

Collaborative regression of expressive bodies using moderation

Y Feng, V Choutas, T Bolkart, D Tzionas, MJ Black

3DV 2021

MeshDiffusion: Score-based generative 3D mesh modeling

Z Liu, Y Feng, MJ Black, D Nowrouzezahrai, L Paull, W Liu

Capturing and animation of body and clothing from monocular video

Y Feng, J Yang, M Pollefeys, MJ Black, T Bolkart

Siggraph Asia 2022

Parameter-efficient orthogonal finetuning via butterfly factorization

W Liu, Z Qiu, Y Feng, Y Xiu, Y Xue, L Yu, H Feng, Z Liu, J Heo, S Peng

ICLR 2024

MonoHair: High-Fidelity Hair Modeling from a Monocular Video

K Wu, L Yang, Z Kuang, Y Feng, X Han, Y Shen, H Fu, K Zhou, Y Zheng

CVPR 2024

Ghost on the Shell: An Expressive Representation of General 3D Shapes

Z Liu, Y Feng, Y Xiu, W Liu, L Paull, MJ Black, B Schölkopf

ICLR 2024

Radu Alexandru Rosu

Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images

RA Rosu, S Saito, Z Wang, C Wu, S Behnke, G Nam

ECCV 2022

PermutoSDF: Fast Multi-View Reconstruction with Implicit Surfaces using Permutohedral Lattices

RA Rosu, S Behnke

CVPR 2023

NeuralMVS: Bridging Multi-View Stereo and Novel View Synthesis

RA Rosu, S Behnke

IJCNN 2022

Nitin Saini

SmartMocap: Joint Estimation of Human and Camera Motion Using Uncalibrated RGB Cameras

N. Saini, C. P. Huang, M. J. Black, A. Ahmad

IEEE Robotics and Automation Letters, 8(6):3206-3213, 2023

AirPose: Multi-View Fusion Network for Aerial 3D Human Pose and Shape Estimation

N. Saini, E. Bonetto, E. Price, A. Ahmad, M. J. Black

IEEE Robotics and Automation Letters, 7(2):4805-4812, IEEE, April 2022

AirCapRL: Autonomous Aerial Human Motion Capture Using Deep Reinforcement Learning

R. Tallamraju, N. Saini, E. Bonetto, M. Pabst, Y. T Liu, M. J. Black, A. Ahmad

IEEE Robotics and Automation Letters, 7(2):4805-4812, IEEE, April 2022

Markerless Outdoor Human Motion Capture Using Multiple Autonomous Micro Aerial Vehicles

N. Saini, E. Price, R. Tallamraju, R. Enficiaud, R. Ludwig, I. Martinović, A. Ahmad, M. Black

ICCV 219

Michael J. Black

Detailed human shape and pose from images

AO Balan, L Sigal, MJ Black, JE Davis, HW Haussecker

CVPR 2007

End-to-end recovery of human shape and pose

A Kanazawa, MJ Black, DW Jacobs, J Malik

CVPR 2018

Keep it SMPL: Automatic estimation of 3D human pose and shape from a single image

F Bogo, A Kanazawa, C Lassner, P Gehler, J Romero, MJ Black

ECCV 2016

Embodied hands: Modeling and capturing hands and bodies together

J Romero, D Tzionas, MJ Black

ACM Transactions on Graphics, (Proc. SIGGRAPH Asia), 36(6):245:1-245:17, 245:1–245:17, ACM, November 2017

Learning a model of facial shape and expression from 4D scans

T Li, T Bolkart, MJ Black, H Li, J Romero

ACM Trans. Graph. 36 (6), 194:1-194:17, 2017

Recovering accurate 3D human pose in the wild using IMUs and a moving camera

T Von Marcard, R Henschel, MJ Black, B Rosenhahn, G Pons-Moll

ECCV 2018

Expressive body capture: 3D hands, face, and body from a single image

G Pavlakos, V Choutas, N Ghorbani, T Bolkart, AAA Osman, D Tzionas, ...

CVPR 2019

Learning to reconstruct 3D human pose and shape via model-fitting in the loop

N Kolotouros, G Pavlakos, K Black, Michael J., Daniilidis

ICCV 2019

Action-conditioned 3d human motion synthesis with transformer vae

M Petrovich, MJ Black, G Varol

CVPR 2021

TEMOS: Generating diverse human motions from textual descriptions

Y Xiu, J Yang, D Tzionas, MJ Black

ECCV 2022

ICON: Implicit clothed humans obtained from normals

Y Xiu, J Yang, D Tzionas, MJ Black

CVPR 2022

BEDLAM: A synthetic dataset of bodies exhibiting detailed lifelike animated motion

MJ Black, P Patel, J Tesch, J Yang

CVPR 2023

WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion

S Shin, J Kim, E Halilaj, MJ Black

CVPR 2024