GroomCap: High-Fidelity Prior-Free Hair Capture
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916672318734336 |
|---|---|
| author | Zhou, Yuxiao Chai, Menglei Wang, Daoye Winberg, Sebastian Wood, Erroll Sarkar, Kripasindhu Gross, Markus Beeler, Thabo |
| author_facet | Zhou, Yuxiao Chai, Menglei Wang, Daoye Winberg, Sebastian Wood, Erroll Sarkar, Kripasindhu Gross, Markus Beeler, Thabo |
| contents | Despite recent advances in multi-view hair reconstruction, achieving strand-level precision remains a significant challenge due to inherent limitations in existing capture pipelines. We introduce GroomCap, a novel multi-view hair capture method that reconstructs faithful and high-fidelity hair geometry without relying on external data priors. To address the limitations of conventional reconstruction algorithms, we propose a neural implicit representation for hair volume that encodes high-resolution 3D orientation and occupancy from input views. This implicit hair volume is trained with a new volumetric 3D orientation rendering algorithm, coupled with 2D orientation distribution supervision, to effectively prevent the loss of structural information caused by undesired orientation blending. We further propose a Gaussian-based hair optimization strategy to refine the traced hair strands with a novel chained Gaussian representation, utilizing direct photometric supervision from images. Our results demonstrate that GroomCap is able to capture high-quality hair geometries that are not only more precise and detailed than existing methods but also versatile enough for a range of applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_00831 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GroomCap: High-Fidelity Prior-Free Hair Capture Zhou, Yuxiao Chai, Menglei Wang, Daoye Winberg, Sebastian Wood, Erroll Sarkar, Kripasindhu Gross, Markus Beeler, Thabo Graphics Despite recent advances in multi-view hair reconstruction, achieving strand-level precision remains a significant challenge due to inherent limitations in existing capture pipelines. We introduce GroomCap, a novel multi-view hair capture method that reconstructs faithful and high-fidelity hair geometry without relying on external data priors. To address the limitations of conventional reconstruction algorithms, we propose a neural implicit representation for hair volume that encodes high-resolution 3D orientation and occupancy from input views. This implicit hair volume is trained with a new volumetric 3D orientation rendering algorithm, coupled with 2D orientation distribution supervision, to effectively prevent the loss of structural information caused by undesired orientation blending. We further propose a Gaussian-based hair optimization strategy to refine the traced hair strands with a novel chained Gaussian representation, utilizing direct photometric supervision from images. Our results demonstrate that GroomCap is able to capture high-quality hair geometries that are not only more precise and detailed than existing methods but also versatile enough for a range of applications. |
| title | GroomCap: High-Fidelity Prior-Free Hair Capture |
| topic | Graphics |
| url | https://arxiv.org/abs/2409.00831 |