Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.02483 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909964035948544 |
|---|---|
| author | Zhou, Xilong Chen, Jianchun Rao, Pramod Teufel, Timo Lyu, Linjie Minasian, Tigran Sotnychenko, Oleksandr Long, Xiao-Xiao Habermann, Marc Theobalt, Christian |
| author_facet | Zhou, Xilong Chen, Jianchun Rao, Pramod Teufel, Timo Lyu, Linjie Minasian, Tigran Sotnychenko, Oleksandr Long, Xiao-Xiao Habermann, Marc Theobalt, Christian |
| contents | We introduce OLATverse, a large-scale dataset comprising around 9M images of 765 real-world objects, captured from multiple viewpoints under a diverse set of precisely controlled lighting conditions. While recent advances in object-centric inverse rendering, novel view synthesis and relighting have shown promising results, most techniques still heavily rely on the synthetic datasets for training and small-scale real-world datasets for benchmarking, which limits their realism and generalization. To address this gap, OLATverse offers two key advantages over existing datasets: large-scale coverage of real objects and high-fidelity appearance under precisely controlled illuminations. Specifically, OLATverse contains 765 common and uncommon real-world objects, spanning a wide range of material categories. Each object is captured using 35 DSLR cameras and 331 individually controlled light sources, enabling the simulation of diverse illumination conditions. In addition, for each object, we provide well-calibrated camera parameters, accurate object masks, photometric surface normals, and diffuse albedo as auxiliary resources. We also construct an extensive evaluation set, establishing the first comprehensive real-world object-centric benchmark for inverse rendering and normal estimation. We believe that OLATverse represents a pivotal step toward integrating the next generation of inverse rendering and relighting methods with real-world data. The full dataset, along with all post-processing workflows, will be publicly released at https://vcai.mpi-inf.mpg.de/projects/OLATverse/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_02483 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OLATverse: A Large-scale Real-world Object Dataset with Precise Lighting Control Zhou, Xilong Chen, Jianchun Rao, Pramod Teufel, Timo Lyu, Linjie Minasian, Tigran Sotnychenko, Oleksandr Long, Xiao-Xiao Habermann, Marc Theobalt, Christian Computer Vision and Pattern Recognition Graphics We introduce OLATverse, a large-scale dataset comprising around 9M images of 765 real-world objects, captured from multiple viewpoints under a diverse set of precisely controlled lighting conditions. While recent advances in object-centric inverse rendering, novel view synthesis and relighting have shown promising results, most techniques still heavily rely on the synthetic datasets for training and small-scale real-world datasets for benchmarking, which limits their realism and generalization. To address this gap, OLATverse offers two key advantages over existing datasets: large-scale coverage of real objects and high-fidelity appearance under precisely controlled illuminations. Specifically, OLATverse contains 765 common and uncommon real-world objects, spanning a wide range of material categories. Each object is captured using 35 DSLR cameras and 331 individually controlled light sources, enabling the simulation of diverse illumination conditions. In addition, for each object, we provide well-calibrated camera parameters, accurate object masks, photometric surface normals, and diffuse albedo as auxiliary resources. We also construct an extensive evaluation set, establishing the first comprehensive real-world object-centric benchmark for inverse rendering and normal estimation. We believe that OLATverse represents a pivotal step toward integrating the next generation of inverse rendering and relighting methods with real-world data. The full dataset, along with all post-processing workflows, will be publicly released at https://vcai.mpi-inf.mpg.de/projects/OLATverse/. |
| title | OLATverse: A Large-scale Real-world Object Dataset with Precise Lighting Control |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2511.02483 |