HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916894063198208 |
|---|---|
| author | Teufel, Timo Gera, Pulkit Zhou, Xilong Iqbal, Umar Rao, Pramod Kautz, Jan Golyanik, Vladislav Theobalt, Christian |
| author_facet | Teufel, Timo Gera, Pulkit Zhou, Xilong Iqbal, Umar Rao, Pramod Kautz, Jan Golyanik, Vladislav Theobalt, Christian |
| contents | Simultaneous relighting and novel-view rendering of digital human representations is an important yet challenging task with numerous applications. Progress in this area has been significantly limited due to the lack of publicly available, high-quality datasets, especially for full-body human captures. To address this critical gap, we introduce the HumanOLAT dataset, the first publicly accessible large-scale dataset of multi-view One-Light-at-a-Time (OLAT) captures of full-body humans. The dataset includes HDR RGB frames under various illuminations, such as white light, environment maps, color gradients and fine-grained OLAT illuminations. Our evaluations of state-of-the-art relighting and novel-view synthesis methods underscore both the dataset's value and the significant challenges still present in modeling complex human-centric appearance and lighting interactions. We believe HumanOLAT will significantly facilitate future research, enabling rigorous benchmarking and advancements in both general and human-specific relighting and rendering techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_09137 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis Teufel, Timo Gera, Pulkit Zhou, Xilong Iqbal, Umar Rao, Pramod Kautz, Jan Golyanik, Vladislav Theobalt, Christian Computer Vision and Pattern Recognition Simultaneous relighting and novel-view rendering of digital human representations is an important yet challenging task with numerous applications. Progress in this area has been significantly limited due to the lack of publicly available, high-quality datasets, especially for full-body human captures. To address this critical gap, we introduce the HumanOLAT dataset, the first publicly accessible large-scale dataset of multi-view One-Light-at-a-Time (OLAT) captures of full-body humans. The dataset includes HDR RGB frames under various illuminations, such as white light, environment maps, color gradients and fine-grained OLAT illuminations. Our evaluations of state-of-the-art relighting and novel-view synthesis methods underscore both the dataset's value and the significant challenges still present in modeling complex human-centric appearance and lighting interactions. We believe HumanOLAT will significantly facilitate future research, enabling rigorous benchmarking and advancements in both general and human-specific relighting and rendering techniques. |
| title | HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.09137 |