Dynamic hair capture using spacetime optimization

Xu, Zexiang; Wu, Hsiang-Tao; Wang, Lvdi; Zheng, Changxi; Tong, Xin; Qi, Yue

doi:10.1145/2661229.2661284

Cited by 38 publications

(26 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each frame, they construct a orientation field using directed ribbons and trace the initial hair model from this field. The initial result could match [27]; c our result. The number of hair in each result is 50 K most of the original hair.…”

Section: Resultsmentioning

confidence: 86%

“…We also compare our approach with cutting-edge dynamic hair capture method [27]. For each frame, they construct a orientation field using directed ribbons and trace the initial hair model from this field.…”

Section: Resultsmentioning

confidence: 99%

“…Aras et al [1] introduced a sketch-based tool for hair modeling, while it was cumbersome for a large number of hair. Xu et al [27] proposed a dynamic hair modeling method, which utilized the motion path analysis and solved space-time consistency to produce realistically dynamic hair models both in geometry and motion details. Yu et al [31] presented a hybrid image-CAD based system, which could reconstruct many hairstyles, but the reconstructed results are not as realistic as captured hair images.…”

Section: Related Workmentioning

confidence: 99%

“…To generate S d , we construct a regular grid of hair volume and diffuse the directions defined on all directed ribbons. This diffusion procedure is similar to [27], and the width of a voxel in all our examples is 2 mm.…”

Section: Constructing Multiple Orientation Fieldsmentioning

confidence: 99%

See 3 more Smart Citations

Realistic hair modeling from a hybrid orientation field

Bao

2016

Vis Comput

Self Cite

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

Section: Resultsmentioning

confidence: 86%

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Constructing Multiple Orientation Fieldsmentioning

confidence: 99%

See 2 more Smart Citations

Realistic hair modeling from a hybrid orientation field

Bao

2016

Vis Comput

Self Cite

View full text Add to dashboard Cite

show abstract

“…Luo et al [LLP*12] present a multi‐view system that relies primarily on orientation fields to recover hair structure, and show that the approach can be used on dynamic hair, although without establishing correspondence over time. The state‐of‐the‐art in capturing temporally‐coherent dynamic hair is the method of Xu et al [XWW*14], who formulate the problem as a spacetime optimization over the projected motion path of local hair strands. The reconstructed geometry is impressive, however the hair animation can only be played as captured without an easy way to edit or re‐direct the animation.…”

Section: Beyond Face Reconstructionmentioning

confidence: 99%

State of the Art on Monocular 3D Face Reconstruction, Tracking, and Applications

Zollhöfer

Thies

Garrido

et al. 2018

Computer Graphics Forum

298

152

View full text Add to dashboard Cite

The computer graphics and vision communities have dedicated long standing efforts in building computerized tools for reconstructing, tracking, and analyzing human faces based on visual input. Over the past years rapid progress has been made, which led to novel and powerful algorithms that obtain impressive results even in the very challenging case of reconstruction from a single RGB or RGB‐D camera. The range of applications is vast and steadily growing as these technologies are further improving in speed, accuracy, and ease of use. Motivated by this rapid progress, this state‐of‐the‐art report summarizes recent trends in monocular facial performance capture and discusses its applications, which range from performance‐based animation to real‐time facial reenactment. We focus our discussion on methods where the central task is to recover and track a three dimensional model of the human face using optimization‐based reconstruction algorithms. We provide an in‐depth overview of the underlying concepts of real‐world image formation, and we discuss common assumptions and simplifications that make these algorithms practical. In addition, we extensively cover the priors that are used to better constrain the under‐constrained monocular reconstruction problem, and discuss the optimization techniques that are employed to recover dense, photo‐geometric 3D face models from monocular 2D data. Finally, we discuss a variety of use cases for the reviewed algorithms in the context of motion capture, facial animation, as well as image and video editing.

show abstract

A motion‐field‐based data‐driven method for hair animation

Bao

2018

Computer Animation & Virtual

Self Cite

View full text Add to dashboard Cite

We propose a motion-field-based data-driven approach that animates static hair models from a set of precomputed motion data. We first sample a motion sequence to construct a motion database from physics-based hair simulation data or dynamic hair capture data. We also define the preliminary definitions of motion states and construct a motion field for this motion database. Finally, we generate a sequence of target hairstyle from the input motion field by strand correspondence and motion control. Experimental results show that our approach achieves comparable quality with physics-based methods but in orders of magnitude faster performance.

show abstract

Dynamic hair capture using spacetime optimization

Cited by 38 publications

References 37 publications

Realistic hair modeling from a hybrid orientation field

Realistic hair modeling from a hybrid orientation field

State of the Art on Monocular 3D Face Reconstruction, Tracking, and Applications

A motion‐field‐based data‐driven method for hair animation

Contact Info

Product

Resources

About