Abstract
We propose a novel technique to extract features from a range image and use them to produce a 3D pen-and-ink style portrait similar to a traditional artistic drawing. Unlike most previous template-based, component-based or example-based face sketching methods, which work from a frontal photograph as input, our system uses a range image as input. Our method runs in real-time for models of moderate complexity, allowing the pose and drawing style to be modified interactively. Portrait drawing in our system makes use of occluding contours and suggestive contours as the most important shape cues. However, current 3D feature line detection methods require a smooth mesh and cannot be reliably applied directly to noisy range images. We thus present an improved silhouette line detection algorithm. Feature edges related to the significant parts of a face are extracted from the range image, connected, and smoothed, allowing us to construct chains of line paths which can then be rendered as desired. We also incorporate various portrait-drawing principles to provide several simple yet effective nonphotorealistic portrait renderers such as a pen-and-ink shader, a hatch shader and a sketch shader. These are able to generate various life-like impressions in different styles from a user-chosen viewpoint. To obtain satisfactory results, we refine rendered output by smoothing changes in line thickness and opacity. We are careful to provide appropriate visual cues to enhance the viewer’s comprehension of the human face. Our experimental results demonstrate the robustness and effectiveness of our approach, and further suggest that our approach can be extended to other 3D geometric objects.
Similar content being viewed by others
References
Gooch B, Reinhard E, Gooch A. Human facial illustrations: Creation and psychophysical evaluation. ACM Trans Graph, 2004, 23(1): 27–44
Hertzmann A, Zorin D. Illustrating smooth surfaces. In: Proc of SIGGRAPH, 2000, 517–526
Isenberg T, Halper N, Strothotte T. Stylizing silhouettes at interactive rates: From silhouette edges to silhouette strokes. In: Proc of EuroGraphics, 2002, 249–258
Kalnins R, Markosian L, Meier B, et al. WYSIWYG NPR: Drawing strokes directly on 3d models. In: Proc of SIGGRAPH, 2002. 755–762
Kalnins R, Davidson P, Markosian L, et al. Coherent stylized silhouettes. ACM Trans Graph, 2003, 22(3): 856–861
Northrup J, Markosian L. Artistic silhouettes: a hybrid ap proach. In: Proc of NPAR, 2000. 31–38
Sousa CM, Buchanan WJ. Computer-generated graphite pencil rendering of 3d polygonal models. In: Proc of EuroGraphics, 1999. 195–208
Winkenbach G, Salesin H D. Computer-generated pen-and-ink illustration. In: Proc of SIGGRAPH, 1994. 91–100
Liang L, Chen H, Xu Y Q, et al. Example-based caricature generation with exaggeration. In: Proc of 10th Pacific Conf on Computer Graphic and Application, 2002. 386–393
Chen H, Liu Z Q, Rose C, et al. Example-based composite sketching of human portraits. In: Proc of NPAR, 2004. 95–153
Tresset P, Leymarie F F. Generative Portrait Sketching. In: 11th Inter Conf on Virtual Systems and Multi-Media, 2005. 739–748
Douglas G R. Drawing Portraits. New York: Watson-Guptill Publications, 1983
Freeman J. Portrait Drawing. Marlborough: Crowood Press, 2006
Blake W, Lawn J. Portrait Drawing: A Step-by-Step Art Instruction Book. New York: Watson-Guptill Publications, 2006
Decarlo D, Finkelstein A, Rusinkiewicz S, et al. Suggestive contours for conveying shape. ACM Trans Graph, 2003, 22(3): 848–855
Decarlo D, Finkelstein A, Rusinkiewicz S. Interactive rendering of suggestive contours with temporal coherence. In: Proc of NPAR, 2004. 15–24
Akleman E. Making caricature with morphing. In: Proc of SIGGRAPH, 1997. 145
Luo Y, Gavrilova M L, Sousa M C. NPAR by example: line drawing facial animation from photographs. In: IEEE Inter Conf on Computer Graphics, Imaging and Visualization, 2006. 514–521
Xu Z J, Chen H, Zhu S C, et al. A hierarchical compositional model for face representation and sketching. IEEE Trans Patt Anal Mach Intell, 2008, 30(6): 955–969
Fujiwara T, Koshimizu H, Fujimura K, et al. 3D modeling system of human face and full 3D facial caricaturing. In: Proc of 3D Digital Imaging and Modeling, 2001. 39–51
Boyer V. An artistic portrait caricature model. In: Proc of Inter Symp of Visual Computing, 2005. 595–600
Cole F, Golovinskiy A, Limpaecher A, et al. Where do people draw lines? ACM Trans Graph, 2008, 22(3): 44–55
Decarlo D, Finkelstein A. Line drawings from 3D models. In: Proc of SIGGRAPH, Course Note, 2005
Decarlo D, Rusinkiewicz S. Highlight lines for conveying shape. In: Proc of NPAR, 2007. 63–70
Lee Y J, Markosian L, Lee S, et al. Line drawings via abstracted shading. ACM Trans Graph, 2007, 26(3): 18
Judd T, Durand F, Adelson E. Apparent ridges for line drawing. ACM Trans Graph, 2007, 26(3): 19
Sun X F, Rosin P L, Martin R R, et al. Fast and effective feature-preserving mesh denoising. IEEE Trans Visual Comput Graph, 2007, 13(5): 925–938
Canny J. A computational approach to edge detection. IEEE Trans Patt Anal Mach Intell, 1986, 8(6): 679–698
Finkelstein A, Salesin D H. Multiresolution curves. In: Proc of SIGGRAPH, 1994, 261–268
Sousa M C, Prusinkiewicz P. A few good lines: suggestive drawing of 3D models. Comput Graph Forum, 2003, 22(3): 381–390
Kass M, Witkin A, Terzopoulos D. Snakes: active contour models. Inter J Comput Vision, 1988, 1(4): 321–331
Mortensen E, Barrett W. Intelligent scissors for image composition. In: Proc of SIGGRAPH, 1995. 191–198
Lake A, Marshall C, Harris M, et al. Stylized rendering techniques for scalable real-time 3d animation. In: Proc of NPAR, 2000. 13–20
Goodwin T, Vollick I, Hertzmann A. Isophote distance: A shading approach to artistic stroke thickness. In: Proc of NPAR, 2007. 53–62
Flynn J P, Bowyer W K, Phillips J P. Assessment of time dependency in face recognition: An initial study. In: Audio and Video-Based Biometric Person Authentication, 2003. 44–51
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by the National Basic Research Program of China (Grant No. 2006CB303102) and the National Natural Science Foundation of China (Grant Nos. 60473103 and 60703028). This work was done during Huang Yuezhu’s visit to Cardiff University under the CSC scholarship
Rights and permissions
About this article
Cite this article
Huang, Y., Martin, R.R., Rosin, P.L. et al. Expressive line drawings of human faces from range images. Sci. China Ser. F-Inf. Sci. 52, 295–307 (2009). https://doi.org/10.1007/s11432-009-0039-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11432-009-0039-3