HTML: A Parametric Hand Texture Model for 3D Hand Reconstruction and Personalization

Qian, Neng; Wang, Jiayi; Mueller, Franziska; Bernard, Florian; Golyanik, Vladislav; Theobalt, Christian

doi:10.1007/978-3-030-58621-8_4

Cited by 51 publications

(49 citation statements)

References 56 publications

(79 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Skin Tone & Textures. We adopt a state-of-the-art hand skin tone & texture model: HTML [35] for realistic appearance on the rendered images. HTML represents the hand's skin color & texture of as continuous parameters in a PCA space.…”

Section: Online Synthesis For Hope Taskmentioning

confidence: 99%

ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis

Li¹,

Yang²,

Zhan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Estimating the articulated 3D hand-object pose from a single RGB image is a highly ambiguous and challenging problem requiring large-scale datasets that contain diverse hand poses, object poses, and camera viewpoints. Most real-world datasets lack this diversity. In contrast, synthetic datasets can easily ensure vast diversity, but learning from them is inefficient and suffers from heavy training consumption. To address the above issues, we propose ArtiBoost, a lightweight online data enrichment method that boosts articulated hand-object pose estimation from the data perspective. ArtiBoost is employed along with a real-world source dataset. During training, ArtiBoost alternatively performs data exploration and synthesis. Art-iBoost can cover various hand-object poses and camera viewpoints based on a Compositional hand-object Configuration and Viewpoint space (CCV-space) and can adaptively enrich the current hard-discernable samples by a mining strategy. We apply ArtiBoost on a simple learning baseline network and demonstrate the performance boost on several hand-object benchmarks. As an illustrative example, with ArtiBoost, even a simple baseline network can outperform the previous start-of-the-art based on Transformer on the HO3D dataset. Our code is available at https://github.com/MVIG-SJTU/ArtiBoost.

show abstract

Section: Online Synthesis For Hope Taskmentioning

confidence: 99%

ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis

Li¹,

Yang²,

Zhan³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The PCA technique is combined to simplify the model. Qian et al [36] consummate MANO by augmenting it with a parametric texture model.…”

Section: Hand Parametric Modelsmentioning

confidence: 99%

“…Zhang et al [53] and Boukhayma et al [4], respectively, propose an end-to-end neural network to predict motion parameters with 2D image as input. Qian et al [36] leverage the network in [4] to obtain the motion parameters of MANO and further to refine the mesh model by photometric loss. Other deep learning-based approaches either leverage depth information [29,32] or combine image and depth information together.…”

Section: Hand Pose Reconstructionmentioning

confidence: 99%

3D hand reconstruction from a single image based on biomechanical constraints

Liu

et al. 2021

Vis Comput

View full text Add to dashboard Cite

This paper investigates the estimate of motion parameters from 3D hand joint positions. We formulate the issue as an inverse kinematics problem with biomechanical constraints and propose a fast and robust iterative approach to address the constrained optimization. It elaborately designs a coordinate descent algorithm to decompose the problem into a sequence of decisions on the transformation around each kinematic node (i.e., joint), while the decision for each node is equivalent to a point matching problem. Addressing the whole optimization then amounts to considering all nodes of the kinematic tree from its root to leaves one by one. This not only accelerates the process but also improves the accuracy of the solution of the inverse kinematic optimization. Experiments show that our approach is able to yield results comparable to and even better than those by the state-of-the-art methods.

show abstract

“…We would like to thank the reviewers for their feedback, Jiayi Wang for the hand texture [24], Jessica Illera for the help with the study, and other members of the MSLab at URJC for their support. This work was funded in part by the European Research Council (ERC Consolidator Grant no.772738 TouchDesign) and the Spanish Ministry of Science (RTI2018-098694-B-I00 VizLearning; PID2019-105579RB-I00/AEI/10.13039/501100011033).…”

Section: Acknowledgmentsmentioning

confidence: 99%