← ArchivePaper2013
Structure-Aware Hair Capture
Multi-view hair capture system that reconstructs coherent, wisp-aware strand geometry from still photographs without special lighting setups.
Abstract
Existing hair capture systems fail to produce strands that reflect the structures of real-world hairstyles. We introduce a system that reconstructs coherent and plausible wisps aware of the underlying hair structures from a set of still images without any special lighting. Our system first discovers locally coherent wisp structures in the reconstructed point cloud and the 3D orientation field, and then uses a novel graph data structure to reason about both the connectivity and directions of the local wisp structures in a global optimization. The wisps are then completed and used to synthesize hair strands which are robust against occlusion and missing data and plausible for animation and simulation. We show reconstruction results for a variety of complex hairstyles including curly, wispy, and messy hair.
How to read this
- Category
- Capture system: structure-aware multi-view hair reconstruction
- Contributions
- A system that reconstructs coherent, plausible wisps from still images without special lighting
- Discovery of locally coherent wisp structures from the point cloud and 3D orientation field
- A graph data structure for globally optimizing wisp connectivity and direction, yielding strands robust to occlusion and missing data and suitable for animation/simulation
- Context
- Addresses the gap in prior hair capture systems that fail to reflect real hairstyle structure, drawing on multi-view stereo and orientation-field reconstruction for hair.
- Correctness
- Assumes enough multi-view coverage to recover a point cloud and orientation field; the global optimization is what fills occluded/missing regions, so plausibility (not measured ground-truth strand accuracy) is the claim, and results span curly, wispy, and messy styles.
- Clarity
- Accessible at a high level; a first pass conveys the wisp-then-global-graph pipeline, a second pass is needed for the graph optimization details.
- How to read it
- Focus on the two stages (local wisp discovery, then global graph optimization) and what makes output simulation-ready; a second pass pays off for the connectivity/direction reasoning.
Builds on
Nothing in the archive, this is a starting point.
Built upon by
Related work
- Robust Hair Capture Using Simulated Examples 2014 / SIGGRAPH
- Single-View Hair Modeling Using a Hairstyle Database 2015 / SIGGRAPH
- Strand-Accurate Multi-View Hair Capture 2019 / CVPR
- Simulation-Ready Hair Capture 2017 / Eurographics
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 →