ICTPolarReal: A Polarized Reflection and Material Dataset of Real World Objects
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915891736739840 |
|---|---|
| author | Yang, Jing Dharanikota, Krithika Jia, Emily Chen, Haiwei Zhao, Yajie |
| author_facet | Yang, Jing Dharanikota, Krithika Jia, Emily Chen, Haiwei Zhao, Yajie |
| contents | Accurately modeling how real-world materials reflect light remains a core challenge in inverse rendering, largely due to the scarcity of real measured reflectance data. Existing approaches rely heavily on synthetic datasets with simplified illumination and limited material realism, preventing models from generalizing to real-world images. We introduce a large-scale polarized reflection and material dataset of real-world objects, captured with an 8-camera, 346-light Light Stage equipped with cross/parallel polarization. Our dataset spans 218 everyday objects across five acquisition dimensions-multiview, multi-illumination, polarization, reflectance separation, and material attributes-yielding over 1.2M high-resolution images with diffuse-specular separation and analytically derived diffuse albedo, specular albedo, and surface normals. Using this dataset, we train and evaluate state-of-the-art inverse and forward rendering models on intrinsic decomposition, relighting, and sparse-view 3D reconstruction, demonstrating significant improvements in material separation, illumination fidelity, and geometric consistency. We hope that our work can establish a new foundation for physically grounded material understanding and enable real-world generalization beyond synthetic training regimes. Project page: https://jingyangcarl.github.io/ICTPolarReal/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_24912 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ICTPolarReal: A Polarized Reflection and Material Dataset of Real World Objects Yang, Jing Dharanikota, Krithika Jia, Emily Chen, Haiwei Zhao, Yajie Computer Vision and Pattern Recognition Accurately modeling how real-world materials reflect light remains a core challenge in inverse rendering, largely due to the scarcity of real measured reflectance data. Existing approaches rely heavily on synthetic datasets with simplified illumination and limited material realism, preventing models from generalizing to real-world images. We introduce a large-scale polarized reflection and material dataset of real-world objects, captured with an 8-camera, 346-light Light Stage equipped with cross/parallel polarization. Our dataset spans 218 everyday objects across five acquisition dimensions-multiview, multi-illumination, polarization, reflectance separation, and material attributes-yielding over 1.2M high-resolution images with diffuse-specular separation and analytically derived diffuse albedo, specular albedo, and surface normals. Using this dataset, we train and evaluate state-of-the-art inverse and forward rendering models on intrinsic decomposition, relighting, and sparse-view 3D reconstruction, demonstrating significant improvements in material separation, illumination fidelity, and geometric consistency. We hope that our work can establish a new foundation for physically grounded material understanding and enable real-world generalization beyond synthetic training regimes. Project page: https://jingyangcarl.github.io/ICTPolarReal/ |
| title | ICTPolarReal: A Polarized Reflection and Material Dataset of Real World Objects |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.24912 |