Towards Unified 3D Hair Reconstruction from Single-View Portraits
Preprint
Abstract
Single-view 3D hair reconstruction is challenging, due to the wide range of shape variations among diverse hairstyles. Current state-of-the-art methods are specialized in recovering un-braided 3D hairs and often take braided styles as their failure cases, because of the inherent difficulty to define priors for complex hairstyles, whether rule-based or data-based. We propose a novel strategy to enable single-view 3D reconstruction for a variety of hair types via a unified pipeline. To achieve this, we first collect a large-scale synthetic multi-view hair dataset SynMvHair with diverse 3D hair in both braided and un-braided styles, and learn two diffusion priors specialized on hair. Then we optimize 3D Gaussian-based hair from the priors with two specially designed modules, i.e. view-wise and pixel-wise Gaussian refinement. Our experiments demonstrate that reconstructing braided and un-braided 3D hair from single-view images via a unified approach is possible and our method achieves the state-of-the-art performance in recovering complex hairstyles. It is worth to mention that our method shows good generalization ability to real images, although it learns hair priors from synthetic data.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Grounding DINO: Marrying DINO with Grounded Pre-training for Open-Set Object Detection2024
- One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion2024
- Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction2023
- Single‐view procedural braided hair modeling through braid unit identificationComputer Animation and Virtual Worlds, 2021
- Hair-GAN: Recovering 3D hair structure from a single image using generative adversarial networksVisual Informatics, 2019
- High-quality hair modeling from a single portrait photoACM Transactions on Graphics, 2015
- Single-view hair modeling using a hairstyle databaseACM Transactions on Graphics, 2015
- Capturing braided hairstylesACM Transactions on Graphics, 2014
- Robust hair capture using simulated examplesACM Transactions on Graphics, 2014
- Dynamic hair manipulation in images and videosACM Transactions on Graphics, 2013