← ArchivePaper2014
Robust Hair Capture Using Simulated Examples
Data-driven capture framework fitting hair strands to multi-view point clouds via a voting algorithm using a database of physics-simulated example strands.
Abstract
We 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.
How to read this
- Category
- Capture method: data-driven hair reconstruction from point clouds
- Contributions
- A data-driven hair capture framework that reconstructs faithful 3D hair models from unprocessed multi-view point clouds with many outliers
- A voting-based fitting algorithm that finds structurally plausible strand configurations using a database of physics-simulated example strands
- Exhaustive sampling of simulation configurations (reduced via symmetry and constrained initial conditions), plus user sketch strokes for constrained styles like ponytails
- Context
- Builds on geometry-driven multi-view hair capture (Luo et al.'s 'Structure-Aware Hair Capture'), replacing purely geometric heuristics with priors drawn from physically simulated example strands.Builds on: Structure-Aware Hair Capture
- Correctness
- Robustness comes from constraining strands to physically simulable examples, which helps with occlusion, layering, and varying wisp lengths; the trade-off is that fidelity depends on how well the sampled simulation space covers the real hairstyle, and difficult constrained styles still need user sketches.
- Clarity
- Accessible; a first pass conveys the simulate-database-then-vote idea, and a second pass pays off for the voting/fitting algorithm and the sampling strategy.
- How to read it
- Read for the pipeline (simulate examples, grow local segments, vote for plausible global structure); focus on what the example database covers and where the user sketch input is required, then a second pass on the voting algorithm if reproducing.
Builds on
Built upon by
Related work
- Structure-Aware Hair Capture 2013 / SIGGRAPH
- Strand-Accurate Multi-View Hair Capture 2019 / CVPR
- Simulation-Ready Hair Capture 2017 / Eurographics
- Single-View Hair Modeling Using a Hairstyle Database 2015 / SIGGRAPH
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 →