← ArchivePaper2015
Single-View Hair Modeling Using a Hairstyle Database
Data-driven pipeline reconstructing complete 3D hairstyles from a single photograph using USC-HairSalon database retrieval and user-guided strand growing.
Abstract
Human hair presents highly convoluted structures and spans an extraordinarily wide range of hairstyles, which is essential for the digitization of compelling virtual avatars but also one of the most challenging to create. Cutting-edge hair modeling techniques typically rely on expensive capture devices and significant manual labor. We introduce a novel data-driven framework that can digitize complete and highly complex 3D hairstyles from a single-view photograph. We first construct a large database of manually crafted hair models from several online repositories. Given a reference photo of the target hairstyle and a few user strokes as guidance, we automatically search for multiple best matching examples from the database and combine them consistently into a single hairstyle to form the large-scale structure of the hair model. We then synthesize the final hair strands by jointly optimizing for the projected 2D similarity to the reference photo, the physical plausibility of each strand, as well as the local orientation coherency between neighboring strands. We demonstrate the effectiveness and robustness of our method on a variety of hairstyles and challenging images, and compare our system with state-of-the-art hair modeling algorithms.
How to read this
- Category
- Method: data-driven single-view hair modeling
- Contributions
- Digitizes complete, complex 3D hairstyles from a single-view photograph plus a few user strokes, avoiding expensive capture rigs and heavy manual labor.
- Builds a large database of hand-crafted hair models and retrieves/combines multiple best-matching examples into the large-scale hair structure.
- Synthesizes final strands by jointly optimizing 2D similarity to the photo, per-strand physical plausibility, and local orientation coherency between neighboring strands.
- Context
- A database-retrieval approach to hair digitization that extends prior capture work such as Hu et al.'s Robust Hair Capture Using Simulated Examples to the single-photo setting.Builds on: Robust Hair Capture Using Simulated Examples
- Correctness
- Quality is bounded by database coverage and the user-provided strokes/photo; the result is a plausible, coherent match to the reference rather than a true measurement of the subject's hair, so unusual styles outside the database are a limitation.
- Clarity
- Accessible; a first pass conveys the retrieve-then-synthesize pipeline, a second pass for the joint strand-optimization terms.
- How to read it
- First pass for the database-retrieval-plus-strand-synthesis structure; second pass on the optimization objectives if building a hair-reconstruction pipeline.
Builds on
Built upon by
Related work
- Structure-Aware Hair Capture 2013 / SIGGRAPH
- A Data-Driven Approach to Four-View Image-Based Hair Modeling 2017 / SIGGRAPH
- Robust Hair Capture Using Simulated Examples 2014 / SIGGRAPH
- NeuralHDHair: Automatic High-Fidelity Hair Modeling from a Single Image Using Implicit Neural Representations 2022 / CVPR
Keywords
This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →