SketchHairSalon: Deep Sketch-based Hair Image Synthesis

Abstract

efficient methods for sketch completion are proposed to automatically complete repetitive braided parts and hair strokes, respectively, thus reducing the workload of users. Based on the trained networks and the two sketch completion strategies, we build an intuitive interface to allow even novice users to design visually pleasing hair images exhibiting various hair structures and appearance via freehand sketches. The qualitative and quantitative evaluations show the advantages of the proposed system over the existing or alternative solutions.

HairCLIP: Design Your Hair by Text and Reference Image

“…Some works [26,50] use mask which explicitly decouples facial attributes including hair as the conditional input for imageto-image translation networks to accomplish hair manipulation. There are also several works [40,49] that use sketches as input to depict the structure and shape of the desired hairstyle. However, such interactions are still relatively costly for users.…”

“…Human hair, as the critical yet challenging component of the face, has long attracted the interest of researchers. In recent years, with the development of deep learning, many conditional GAN-based hair editing methods [26,40,49] can produce satisfactory editing results. Most of these methods use well-drawn sketches [20,40,49] or masks [26,40] as the input of image-to-image translation networks to produce the manipulated results.…”

NeuralHDHair: Automatic High-fidelity Hair Modeling from a Single Image Using Implicit Neural Representations

“…However, there are some problems with such a two-step mechanism. First, since an 2D orientation map is only a filtered version of the input hair growing information [24], using the 2D orientation map alone to bridge the domain gap between real and synthetic data would unavoidably lose hair details (e.g., the relationship of occlusive strands [33]). Second, the existing methods for inferring 3D orientation fields are either time-consuming due to the use of a complex searching and matching process based on a large hair dataset [6,11], or liable to over-smoothness due to the use of deep networks to directly achieve image-to-voxel inference [36].…”