Single-view hair modeling for portrait manipulation

Chai, Menglei; Wang, Lvdi; Weng, Yanlin; Yu, Yizhou; Guo, Baining; Zhou, Kun

doi:10.1145/2185520.2335467

Cited by 20 publications

(37 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To popularize hair capture for end-users, existing methods offer various tradeoffs among setup, quality, and robustness, e.g. thermal imaging [17], capturing from multiple views [19] versus single view [9], or requiring different amounts and types of user inputs [11,10,42]. Such methods can reduce manual edits but also limit the output effects to the captured data at hand.…”

Section: Hair Capturementioning

confidence: 99%

“…Human hair is volumetric and often consists of highly intricate 3D structures, such as strands, wisps, buns, and braids, which are difficult to design with traditional 2D interfaces. 3D hair digitization and data-driven techniques can reduce the need for manual labor [27,11,10,25,19,9], but afford limited control for real production environments.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

HairBrush for Immersive Data-Driven Hair Modeling

Nagano¹,

Chen

et al. 2019

Proceedings of the 32nd Annual ACM Symposium on User Interface Software and Technology

View full text Add to dashboard Cite

While hair is an essential component of virtual humans, it is also one of the most challenging digital assets to create. Existing automatic techniques lack the generality and flexibility to create rich hair variations, while manual authoring interfaces often require considerable artistic skills and efforts, especially for intricate 3D hair structures that can be difficult to navigate. We propose an interactive hair modeling system that can help create complex hairstyles in minutes or hours that would otherwise take much longer with existing tools. Modelers, including novice users, can focus on the overall hairstyles and local hair deformations, as our system intelligently suggests the desired hair parts. Our method combines the flexibility of manual authoring and the convenience of data-driven automation. Since hair contains intricate 3D structures such as buns, knots, and strands, they are inherently challenging to create using traditional 2D interfaces. Our system provides a new 3D hair authoring interface for immersive interaction in virtual reality (VR). Users can draw high-level guide strips, from which our system predicts the most plausible hairstyles via a deep neural network trained from a professionally curated dataset. Each hairstyle in our dataset is composed of multiple variations, serving as blend-shapes to fit the user drawings via global blending and local deformation. The fitted hair models are visualized as interactive suggestions that the user can select, modify, or ignore. We conducted a user study to confirm that our system can significantly reduce manual labor while improve the output quality for modeling a variety of head and facial hairstyles that are challenging to create via existing techniques.

show abstract

Section: Hair Capturementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

HairBrush for Immersive Data-Driven Hair Modeling

Nagano¹,

Chen

et al. 2019

Proceedings of the 32nd Annual ACM Symposium on User Interface Software and Technology

View full text Add to dashboard Cite

show abstract

“…At runtime, the tracked head motion and expressions of the actor are transferred to animate the blendshape model, from which a novel image is rendered. To handle hair, it uses a single-view hair modeling technique [Chai et al 2012] to reconstruct a strand-based 3D hair model, which is also transformed together with the face model and rendered into the final result. As only one input image is used, the resulting avatars are not very expressive and do not have fine-scale details such as dynamic wrinkles.…”

Section: Related Workmentioning

confidence: 99%

Real-time facial animation with image-based dynamic avatars

et al. 2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…Chai et al [6,7] demonstrated a single-view hair modeling for manipulation on portrait images and videos. Echevarria et al [9] generated a printable 3D surface with stylized color and geometric details, but they could not reconstruct highly detailed individual hair strands.…”

Section: Related Workmentioning

confidence: 99%

“…Figure 1 shows the pipeline of our method. A set of 2D strand segments with high confidence (denoted as SD) is traced from the input images by the strand tracing method in [7]. Then the patch-based multi-view stereo algorithm (PMVS) [11] is used to reconstruct point cloud with normal.…”

Section: Overviewmentioning

confidence: 99%

Realistic hair modeling from a hybrid orientation field

Bao

2016

Vis Comput

View full text Add to dashboard Cite

Image-based hair modeling methods enable artists to produce abundant 3D hair models. However, the reconstructed hair models could not preserve the structural details, such as uniformly distributed hair roots, interior strands growing in line with real distribution and exterior strands similar to images. In this paper, we propose a novel approach to construct a realistic 3D hair model from a hybrid orientation field. Our hybrid orientation field is generated from four fields. The first field makes the surface structure of a hairstyle be similar to the input images as much as possible. The second field makes the hair roots and interior hair strands be consistent with actual distribution. The tracing hair strands can be confined to the hair volume according to the third field. And the fourth field makes the growing direction of one point at a strand be compatible with its predecessor. To generate these fields, we construct high-confidence 3D strand segments from the orientation field of point cloud and 2D traced strands. Hair strands automatically grow from uniformly distributed hair roots according to the hybrid orientation field. We use energy minimization strategy to optimize the entire 3D hair model. We demonstrate that our approach can preserve structural details of 3D hair models.Keywords Image-based hair modeling · Hybrid orientation field · Fractional anisotropy · Preserving structural details · Tracing hair strand Electronic supplementary material The online version of this article (

show abstract

Single-view hair modeling for portrait manipulation

Cited by 20 publications

References 12 publications

HairBrush for Immersive Data-Driven Hair Modeling

HairBrush for Immersive Data-Driven Hair Modeling

Real-time facial animation with image-based dynamic avatars

Realistic hair modeling from a hybrid orientation field

Contact Info

Product

Resources

About