Dynamic hair modeling from monocular videos using deep neural networks

Yang, Lingchen; Shi, Zefeng; Zheng, Youyi; Zhou, Kun

doi:10.1145/3355089.3356511

Cited by 30 publications

(27 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently deep learning-based methods have been successfully applied for 3D animations of human faces [27], [28], hair [29], [30] and garments [5], [31]. As for garment synthesis, some approaches [4], [23], [32] are proposed to utilize a two-stream strategy consisting of global garment fit and local wrinkle enhancement.…”

Section: Cloth Animationmentioning

confidence: 99%

Deep Deformation Detail Synthesis for Thin Shell Models

Chen¹,

Gao²,

Yang³

et al. 2021

Preprint

View full text Add to dashboard Cite

In physics-based cloth animation, rich folds and detailed wrinkles are achieved at the cost of expensive computational resources and huge labor tuning. Data-driven techniques make efforts to reduce the computation significantly by utilizing a preprocessed database. One type of methods relies on human poses to synthesize fitted garments, but these methods cannot be applied to general cloth animations. Another type of methods adds details to the coarse meshes, which does not have such restrictions. However, existing works usually utilize coordinate-based representations which cannot cope with large-scale deformation, and requires dense vertex correspondences between coarse and fine meshes. Moreover, as such methods only add details, they require coarse meshes to be sufficiently close to fine meshes, which can be either impossible, or require unrealistic constraints to be applied when generating fine meshes. To address these challenges, we develop a temporally and spatially as-consistent-as-possible deformation representation (named TS-ACAP) and design a DeformTransformer network to learn the mapping from low-resolution meshes to ones with fine details. This TS-ACAP representation is designed to ensure both spatial and temporal consistency for sequential large-scale deformations from cloth animations. With this TS-ACAP representation, our DeformTransformer network first utilizes two mesh-based encoders to extract the coarse and fine features using shared convolutional kernels, respectively. To transduct the coarse features to the fine ones, we leverage the Transformer network that consists of frame-level attention mechanisms to ensure temporal coherence of the prediction. Experimental results show that our method is able to produce reliable and realistic animations in various datasets at high frame rates: 10 ∼ 35 times faster than physics-based simulation, with superior detail synthesis abilities compared to existing methods.

show abstract

Section: Cloth Animationmentioning

confidence: 99%

Deep Deformation Detail Synthesis for Thin Shell Models

Chen¹,

Gao²,

Yang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Dynamic Hair Capture. Compared to the vast body of work on hair geometry acquisition, the work on hair dynamics [11,70,72,76] acquisition is much less. Zhang et al [76] uses hair simulation to enforce better temporal consistency over a per-frame hair reconstruction result.…”

Section: Related Workmentioning

confidence: 99%

“…Xu et al [70] performs visual tracking by aligning per-frame reconstruction of hair strands with motion paths of hair strands on a horizontal slice of a video volume. Yang et al [72] developed a deep learning framework for hair tracking using indirect supervision from 2D hair segmentation and a digital 3D hair dataset. However those methods mainly focus on geometry modeling and are not photometrically accurate or do not support drivable animation.…”

Section: Related Workmentioning

confidence: 99%

HVH: Learning a Hybrid Neural Volumetric Representation for Dynamic Hair Performance Capture

Wang¹,

Nam²,

Stuyck³

et al. 2021

Preprint

View full text Add to dashboard Cite

Capturing and rendering life-like hair is particularly challenging due to its fine geometric structure, the complex physical interaction and its non-trivial visual appearance. Yet, hair is a critical component for believable avatars. In this paper, we address the aforementioned problems: 1) we use a novel, volumetric hair representation that is composed of thousands of primitives. Each primitive can be rendered efficiently, yet realistically, by building on the latest advances in neural rendering. 2) To have a reliable control signal, we present a novel way of tracking hair on the strand level. To keep the computational effort manageable, we use guide hairs and classic techniques to expand those into a dense hood of hair. 3) To better enforce temporal consistency and generalization ability of our model, we further optimize the 3D scene flow of our representation with multiview optical flow, using volumetric raymarching. Our method can not only create realistic renders of recorded multi-view sequences, but also create renderings for new hair configurations by providing new control signals. We compare our method with existing work on viewpoint synthesis and drivable animation and achieve stateof-the-art results. Please check out our project website at https://ziyanw1.github.io/hvh/.

show abstract

“…The machine learning methods consider player's choices in the animation industry for games and analyze diseases to contribute to the decision-making mechanism [2,6,7,15,34,46]. With the successful implementations of machine learning, attacks on the machine learning process and counter-attack methods and incrementing robustness of learning have become hot research topics in recent years [24,27,31,37,51]. The presence of negative data samples or an attack on the model can lead to producing incorrect results in the predictions and classifications even in the advanced models.…”

Section: Introductionmentioning

confidence: 99%