HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis
This addresses a critical gap for researchers in computer vision and graphics by providing a foundational dataset, though it is incremental as it focuses on data collection rather than new methods.
The authors tackled the lack of public datasets for full-body human relighting and novel-view synthesis by introducing HumanOLAT, a large-scale dataset with multi-view captures under various illuminations, which they used to evaluate state-of-the-art methods and highlight remaining challenges.
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.