STITCH: Structure Tensor Informed Topologically Coherent Hair Reconstruction

Abstract Hair reconstruction remains fundamentally challenging due to the filamentary nature of strands, strong self‐occlusion, and the difficulty of recovering globally consistent 1D structure from multi‐view observations. While multi‐view cues provide complementary geometric evidence, existing approaches based on learned priors or implicit volumetric representations often struggle to generalize across diverse hairstyles or preserve fine directional detail. Learned methods can over‐constrain global structure due to limited training diversity, while implicit orientation fields tend to collapse multi‐modal strand orientations into locally averaged estimates, losing high‐frequency directional variation in heavily occluded regions. We depart from these approaches by introducing a sparse hierarchical reconstruction framework based on an ambiguous structure tensor representation that encodes local orientation distributions without committing to explicit strand directions. Our key insight is that preserving directional ambiguity during reconstruction enables robust aggregation of multi‐view evidence, postponing directional commitment until sufficient global information is available to enforce consistency. To reconstruct heavily occluded regions, we introduce a boundary‐driven propagation strategy that transfers reliable surface structure into the interior through locally coherent helical continuation, enabling unobserved geometry to remain consistent with surrounding strand flow. We further introduce a consensus‐based disambiguation mechanism that resolves tensor ambiguity and helical chirality into globally consistent strand growth directions, together with a cross‐view orientation regularization stage that stabilizes early surface reconstruction into thin, strand‐aligned structures. Extensive experiments demonstrate that our method significantly improves strand‐level fidelity and structural coherence on highly occluded, curly, and geometrically complex hairstyles.

Authors

Institutions

Publication Details

Journal
Computer Graphics Forum
Published
2026-11-13
DOI
https://doi.org/10.1111/cgf.70640
Primary Topic
3D Shape Modeling and Analysis
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

STITCH: Structure Tensor Informed Topologically Coherent Hair Reconstruction

Markus Plack, Alireza Vafaei, Reinhard Klein, Jan Spindler et al.
2 links
Computer Graphics Forum
3D Shape Modeling and Analysis
article

STITCH: Structure Tensor Informed Topologically Coherent Hair Reconstruction

Markus Plack, Alireza Vafaei, Reinhard Klein, Jan Spindler, Patrick Stotko, Hannah Dröge
article en

Abstract

Abstract Hair reconstruction remains fundamentally challenging due to the filamentary nature of strands, strong self‐occlusion, and the difficulty of recovering globally consistent 1D structure from multi‐view observations. While multi‐view cues provide complementary geometric evidence, existing approaches based on learned priors or implicit volumetric representations often struggle to generalize across diverse hairstyles or preserve fine directional detail. Learned methods can over‐constrain global structure due to limited training diversity, while implicit orientation fields tend to collapse multi‐modal strand orientations into locally averaged estimates, losing high‐frequency directional variation in heavily occluded regions. We depart from these approaches by introducing a sparse hierarchical reconstruction framework based on an ambiguous structure tensor representation that encodes local orientation distributions without committing to explicit strand directions. Our key insight is that preserving directional ambiguity during reconstruction enables robust aggregation of multi‐view evidence, postponing directional commitment until sufficient global information is available to enforce consistency. To reconstruct heavily occluded regions, we introduce a boundary‐driven propagation strategy that transfers reliable surface structure into the interior through locally coherent helical continuation, enabling unobserved geometry to remain consistent with surrounding strand flow. We further introduce a consensus‐based disambiguation mechanism that resolves tensor ambiguity and helical chirality into globally consistent strand growth directions, together with a cross‐view orientation regularization stage that stabilizes early surface reconstruction into thin, strand‐aligned structures. Extensive experiments demonstrate that our method significantly improves strand‐level fidelity and structural coherence on highly occluded, curly, and geometrically complex hairstyles.

Computer Graphics Forum
University of Bonn (DE), Lamarr Institute for Machine Learning and Artificial Intelligence (DE)
Bundesministerium für Bildung und Forschung, Ministerium für Wirtschaft, Innovation, Digitalisierung und Energie des Landes Nordrhein-Westfalen, European Regional Development Fund
3D Shape Modeling and Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon