GarVerseLOD: High-Fidelity 3D Garment Reconstruction from a Single In-the-Wild Image using a Dataset with Levels of Details
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929577103720448 |
|---|---|
| author | Luo, Zhongjin Liu, Haolin Li, Chenghong Du, Wanghao Jin, Zirong Sun, Wanhu Nie, Yinyu Chen, Weikai Han, Xiaoguang |
| author_facet | Luo, Zhongjin Liu, Haolin Li, Chenghong Du, Wanghao Jin, Zirong Sun, Wanhu Nie, Yinyu Chen, Weikai Han, Xiaoguang |
| contents | Neural implicit functions have brought impressive advances to the state-of-the-art of clothed human digitization from multiple or even single images. However, despite the progress, current arts still have difficulty generalizing to unseen images with complex cloth deformation and body poses. In this work, we present GarVerseLOD, a new dataset and framework that paves the way to achieving unprecedented robustness in high-fidelity 3D garment reconstruction from a single unconstrained image. Inspired by the recent success of large generative models, we believe that one key to addressing the generalization challenge lies in the quantity and quality of 3D garment data. Towards this end, GarVerseLOD collects 6,000 high-quality cloth models with fine-grained geometry details manually created by professional artists. In addition to the scale of training data, we observe that having disentangled granularities of geometry can play an important role in boosting the generalization capability and inference accuracy of the learned model. We hence craft GarVerseLOD as a hierarchical dataset with levels of details (LOD), spanning from detail-free stylized shape to pose-blended garment with pixel-aligned details. This allows us to make this highly under-constrained problem tractable by factorizing the inference into easier tasks, each narrowed down with smaller searching space. To ensure GarVerseLOD can generalize well to in-the-wild images, we propose a novel labeling paradigm based on conditional diffusion models to generate extensive paired images for each garment model with high photorealism. We evaluate our method on a massive amount of in-the-wild images. Experimental results demonstrate that GarVerseLOD can generate standalone garment pieces with significantly better quality than prior approaches. Project page: https://garverselod.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_03047 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GarVerseLOD: High-Fidelity 3D Garment Reconstruction from a Single In-the-Wild Image using a Dataset with Levels of Details Luo, Zhongjin Liu, Haolin Li, Chenghong Du, Wanghao Jin, Zirong Sun, Wanhu Nie, Yinyu Chen, Weikai Han, Xiaoguang Computer Vision and Pattern Recognition Graphics Neural implicit functions have brought impressive advances to the state-of-the-art of clothed human digitization from multiple or even single images. However, despite the progress, current arts still have difficulty generalizing to unseen images with complex cloth deformation and body poses. In this work, we present GarVerseLOD, a new dataset and framework that paves the way to achieving unprecedented robustness in high-fidelity 3D garment reconstruction from a single unconstrained image. Inspired by the recent success of large generative models, we believe that one key to addressing the generalization challenge lies in the quantity and quality of 3D garment data. Towards this end, GarVerseLOD collects 6,000 high-quality cloth models with fine-grained geometry details manually created by professional artists. In addition to the scale of training data, we observe that having disentangled granularities of geometry can play an important role in boosting the generalization capability and inference accuracy of the learned model. We hence craft GarVerseLOD as a hierarchical dataset with levels of details (LOD), spanning from detail-free stylized shape to pose-blended garment with pixel-aligned details. This allows us to make this highly under-constrained problem tractable by factorizing the inference into easier tasks, each narrowed down with smaller searching space. To ensure GarVerseLOD can generalize well to in-the-wild images, we propose a novel labeling paradigm based on conditional diffusion models to generate extensive paired images for each garment model with high photorealism. We evaluate our method on a massive amount of in-the-wild images. Experimental results demonstrate that GarVerseLOD can generate standalone garment pieces with significantly better quality than prior approaches. Project page: https://garverselod.github.io/ |
| title | GarVerseLOD: High-Fidelity 3D Garment Reconstruction from a Single In-the-Wild Image using a Dataset with Levels of Details |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2411.03047 |