Dynamic hair manipulation in images and videos

Chai, Menglei; Wang, Lvdi; Weng, Yanlin; Jin, Xiaogang; Zhou, Kun

doi:10.1145/2461912.2461990

Cited by 81 publications

(48 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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%

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

Section: Related Workmentioning

confidence: 99%

Realistic hair modeling from a hybrid orientation field

Bao

2016

Vis Comput

View full text Add to dashboard Cite

show abstract

“…Chai et al [2012] introduced a method to create approximate 3D strands from a single image that match the inter-strand occlusions and the fitted head model. This system has been recently extended to handle single video input to create hair animations [Chai et al 2013], but is limited to relatively simple hairstyles. Beeler et al [2012] introduced a multi-view stereo system to reconstruct short facial hair by strand-level matching.…”

Section: Related Workmentioning

confidence: 99%

Robust hair capture using simulated examples

Luo

et al. 2014

ACM Trans. Graph.

View full text Add to dashboard Cite

Figure 1: Our system takes as input a few images (a) and employs a database of simulated example strands (b) to discover structurally plausible configurations from the reconstructed cover strands (c) for final strand synthesis (d). Our method robustly fits example strands to the cover strands which are computed from unprocessed outlier affected input data (e) to generate compelling reconstruction results (f). In contrast, the state-of-the-art method of [Luo et al. 2013a] fails in the presence of strong outliers (g). AbstractWe introduce a data-driven hair capture framework based on example strands generated through hair simulation. Our method can robustly reconstruct faithful 3D hair models from unprocessed input point clouds with large amounts of outliers. Current state-of-the-art techniques use geometrically-inspired heuristics to derive global hair strand structures, which can yield implausible hair strands for hairstyles involving large occlusions, multiple layers, or wisps of varying lengths. We address this problem using a voting-based fitting algorithm to discover structurally plausible configurations among the locally grown hair segments from a database of simulated examples. To generate these examples, we exhaustively sample the simulation configurations within the feasible parameter space constrained by the current input hairstyle. The number of necessary simulations can be further reduced by leveraging symmetry and constrained initial conditions. The final hairstyle can then be structurally represented by a limited number of examples. To handle constrained hairstyles such as a ponytail of which realistic simulations are more difficult, we allow the user to sketch a few strokes to generate strand examples through an intuitive interface. Our approach focuses on robustness and generality. Since our method is structurally plausible by construction, we ensure an improved control during hair digitization and avoid implausible hair synthesis for a wide range of hairstyles.

show abstract

“…For example, the methods by [Chai et al 2012;Chai et al 2013;Yu et al 2014] allow the users to manually sketch over input images and/or videos to guide the modeling and editing process. However, as pointed out in [Yu et al 2014], capturing and modeling braids remain a major challenge, especially for the more complex structures.…”

Section: Previous Workmentioning

confidence: 99%

Capturing braided hairstyles

Luo

et al. 2014

ACM Trans. Graph.

View full text Add to dashboard Cite

(a) input photo (b) input mesh (c) extracted structure (d) output strands (e) another view of (a) (f) another view of (d) Figure 1: Capturing a five-strand Dutch braid. We capture the braided hairstyle (a) using a Kinect sensor and obtain an input mesh with a local 3D orientation for each vertex (b). Based on the information provided by the example patches in a database, we extract the centerlines (c) of the braid structure to synthesize final output strands (d). (e) and (f) show the input reference photo and our output strands from another viewpoint. AbstractFrom fishtail to princess braids, these intricately woven structures define an important and popular class of hairstyle, frequently used for digital characters in computer graphics. In addition to the challenges created by the infinite range of styles, existing modeling and capture techniques are particularly constrained by the geometric and topological complexities. We propose a data-driven method to automatically reconstruct braided hairstyles from input data obtained from a single consumer RGB-D camera. Our approach covers the large variation of repetitive braid structures using a family of compact procedural braid models. From these models, we produce a database of braid patches and use a robust random sampling approach for data fitting. We then recover the input braid structures using a multi-label optimization algorithm and synthesize the intertwining hair strands of the braids. We demonstrate that a minimal capture equipment is sufficient to effectively capture a wide range of complex braids with distinct shapes and structures.

show abstract

Dynamic hair manipulation in images and videos

Cited by 81 publications

References 43 publications

Realistic hair modeling from a hybrid orientation field

Realistic hair modeling from a hybrid orientation field

Robust hair capture using simulated examples

Capturing braided hairstyles

Contact Info

Product

Resources

About