Prof. Dr. Siyu Tang

Authors:  Shaofei Wang,  Katja Schwarz,  Andreas Geiger,  Siyu Tang

Given sparse multi-view videos, ARAH learns animatable clothed human avatars that have detailed pose-dependent geometry/appearance and generalize to out-of-distribution poses.

Authors:  Kaifeng Zhao,  Shaofei Wang,  Yan Zhang,  Thabo Beeler,  Siyu Tang

Synthesizing natural interactions between virtual humans and their 3D environments is critical for numerous applications, such as computer games and AR/VR experiences. We propose COINS, for COmpositional INteraction Synthesis with Semantic Control.

Authors: Siwei Zhang, Qianli Ma, Yan Zhang, Zhiyin Qian, Taein Kwon, Marc Pollefeys, Federica Bogo and Siyu Tang

EgoBody is a large-scale egocentric dataset for human 3D motion and social interactions in 3D scenes. We employ Microsoft HoloLens2 headsets to record rich egocentric data streams (including RGB, depth, eye gaze, head and hand tracking). To obtain accurate 3D ground-truth, we calibrate the headset with a multi-Kinect rig and fit expressive SMPL-X body meshes to multi-view RGB-D frames, reconstructing 3D human poses and shapes relative to the scene.

Authors: Yan Wu, Jiahao Wang, Yan Zhang, Siwei Zhang, Otmar Hilliges, Fisher Yu and Siyu Tang

Our goal is to synthesize whole-body grasping motion. Given a 3D object, we aim to generate diverse and natural whole-body human motions that approach and grasp the object.

Authors:  Marko Mihajlovic,  Aayush Bansal,  Michael Zollhoefer,  Siyu Tang,  Shunsuke Saito

KeypointNeRF is a generalizable neural radiance field for virtual avatars.

Authors: Yan Zhang, and Siyu Tang

We propose GAMMA, an automatic and scalable solution, to populate the 3D scene with diverse digital humans. The digital humans have 1) varied body shapes, 2) realistic and perpetual motions to reach goals, and 3) plausible body-ground contact.

Authors:  Marko Mihajlovic,  Shunsuke Saito,  Aayush Bansal,  Michael Zollhoefer, and  Siyu Tang

COAP is a novel neural implicit representation for articulated human bodies that provides an efficient mechanism for modeling self-contacts and interactions with 3D environments.

Authors:  Vassilis Choutas,  Lea Müller,  Chun-Hao Paul Huang,  Siyu Tang,  Dimitrios Tzionas,  Michael Black

We exploit the anthropometric measurements and linguistic shape attributes in several novel ways to train a neural network, called SHAPY, that regresses 3D human pose and shape from an RGB image.

Authors:  Taein Kwon, Bugra Tekin, Siyu Tang, Marc Pollefeys

Temporal alignment of fine-grained human actions in videos is important for numerous applications in computer vision, robotics, and mixed reality.

Authors:  Hongwei Yi, Chun-Hao Paul Huang, Dimitrios Tzionas, Muhammed Kocabas, Mohamed Hassan, Siyu Tang, Justus Thies, Michael Black

Humans are in constant contact with the world as they move through it and interact with it. This contact is a vital source of information for understanding 3D humans, 3D scenes, and the interactions between them.

Authors: Shaofei Wang, Marko Mihajlovic, Qianli Ma, Andreas Geiger, Siyu Tang

MetaAvatar is meta-learned model that represents generalizable and controllable neural signed distance fields (SDFs) for clothed humans. It can be fast fine-tuned to represent unseen subjects given as few as 8 monocular depth images.

Authors: Korrawe Karunratanakul, Adrian Spurr, Zicong Fan, Otmar Hilliges, Siyu Tang

We present HALO, a neural occupancy representation for articulated hands that produce implicit hand surfaces from input skeletons in a differentiable manner.

Authors: Zicong Fan, Adrian Spurr, Muhammed Kocabas, Siyu Tang, Michael J. Black and Otmar Hilliges

In this paper we demonstrate that self-similarity, and the resulting ambiguities in assigning pixel observations to the respective hands and their parts, is a major cause of the final 3D pose error. Motivated by this insight, we propose DIGIT, a novel method for estimating the 3D poses of two interacting hands from a single monocular image.

Authors: Miao Liu, Dexin Yang, Yan Zhang, Zhaopeng Cui, James M. Rehg, Siyu Tang

We seek to reconstruct 4D second-person human body meshes that are grounded on the 3D scene captured in an egocentric view. Our method exploits 2D observations from the entire video sequence and the 3D scene context to optimize human body models over time, and thereby leads to more accurate human motion capture and more realistic human-scene interaction.

Authors: Qianli Ma, Jinlong Yang, Siyu Tang and Michael J. Black

We introduce POP — a point-based, unified model for multiple subjects and outfits that can turn a single, static 3D scan into an animatable avatar with natural pose-dependent clothing deformations.

Authors: Qianli Ma, Jinlong Yang, Siyu Tang and Michael J. Black

We introduce POP — a point-based, unified model for multiple subjects and outfits that can turn a single, static 3D scan into an animatable avatar with natural pose-dependent clothing deformations.

Authors: Siwei Zhang, Yan Zhang, Federica Bogo, Marc Pollefeys and Siyu Tang

LEMO learns motion priors from a larger scale mocap dataset and proposes a multi-​stage optimization pipeline to enable 3D motion reconstruction in complex 3D scenes.

Authors: Lea Müller, Ahmed A. A. Osman, Siyu Tang, Chun-Hao P. Huang and Michael J. Black

we develop new datasets and methods that significantly improve human pose estimation with self-contact.

Authors: Yan Zhang, Michael J. Black and Siyu Tang

"We are more than our joints", or MOJO for short, is a solution to stochastic motion prediction of expressive 3D bodies. Given a short motion from the past, MOJO generates diverse plausible motions in the near future.

Authors: Marko Mihajlovic, Yan Zhang, Michael J. Black and Siyu Tang

LEAP is a neural network architecture for representing volumetric animatable human bodies. It follows traditional human body modeling techniques and leverages a statistical human prior to generalize to unseen humans.

Authors: Shaofei Wang, Andreas Geiger and Siyu Tang

Registering point clouds of dressed humans to parametric human models is a challenging task in computer vision. We propose novel piecewise transformation fields (PTF), a set of functions that learn 3D translation vectors which facilitates occupancy learning, joint-​rotation estimation and mesh registration.

Authors: Qianli Ma, Shunsuke Saito, Jinlong Yang, Siyu Tang and Michael J. Black

SCALE models 3D clothed humans with hundreds of articulated surface elements, resulting in avatars with realistic clothing that deforms naturally even in the presence of topological change.

Authors: Korrawe Karunratanakul, Jinlong Yang, Yan Zhang, Michael Black, Krikamol Muandet, Siyu Tang

Capturing and synthesizing hand-​object interaction is essential for understanding human behaviours, and is key to a number of applications including VR/AR, robotics and human-​computer interaction. 

Authors: Siwei Zhang, Yan Zhang, Qianli Ma, Michael J. Black, Siyu Tang

Automated synthesis of realistic humans posed naturally in a 3D scene is essential for many applications. In this paper we propose explicit representations for the 3D scene and the person-​scene contact relation in a coherent manner.

Authors: Yan Zhang, Michael J. Black, Siyu Tang

In this work, our goal is to generate significantly longer, or “perpetual”, motion: given a short motion sequence or even a static body pose, the goal is to generate non-​deterministic ever-​changing human motions in the future.

Authors: Miao Liu, Siyu Tang, Yin Li, and James M. Rehg

We address the challenging task of anticipating human-​object interaction in first person videos. We adopt intentional hand movement as a future representation and propose a novel deep network that jointly models and predicts the egocentric hand motion, interaction hotspots and future action.

Authors: Xucong Zhang, Seonwook Park, Thabo Beeler, Derek Bradley, Siyu Tang , Otmar Hilliges

We propose the ETH-​XGaze dataset: a large scale (over 1 million samples) gaze estimation dataset with high-​resolution images under extreme head poses and gaze directions.

Authors: Yan Zhang, Mohamed Hassan, Heiko Neumann, Michael J. Black, Siyu Tang

We present a fully-​automatic system that takes a 3D scene and generates plausible 3D human bodies that are posed naturally in that 3D scene.

Authors: Qianli Ma, Jinlong Yang, Anurag Ranjan, Sergi Pujades, Gerard Pons-​Moll, Siyu Tang, and Michael J. Black

CAPE is a Graph-CNN based generative model for dressing 3D meshes of human body. It is compatible with the popular body model, SMPL, and can generalize to diverse body shapes and body poses. The CAPE Dataset provides SMPL mesh registration of 4D scans of people in clothing, along with registered scans of the ground truth body shapes under clothing.