Simulating Dual-Pixel Images From Ray Tracing For Depth Estimation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915745103872000 |
|---|---|
| author | He, Fengchen Zhao, Dayang Xu, Hao Quan, Tingwei Zeng, Shaoqun |
| author_facet | He, Fengchen Zhao, Dayang Xu, Hao Quan, Tingwei Zeng, Shaoqun |
| contents | Many studies utilize dual-pixel (DP) sensor phase characteristics for various applications, such as depth estimation and deblurring. However, since the DP image features are entirely determined by the camera hardware, DP-depth paired datasets are very scarce, especially when performing depth estimation on customized cameras. To overcome this, studies simulate DP images using ideal optical system models. However, these simulations often violate real optical propagation laws, leading to poor generalization to real DP data. To address this, we investigate the domain gap between simulated and real DP data, and propose solutions using the Simulating DP images from ray tracing (Sdirt) scheme. The Sdirt generates realistic DP images via ray tracing and integrates them into the depth estimation training pipeline. Experimental results show that models trained with Sdirt-simulated images generalize better to real DP data. The code and collected datasets will be available at github.com/LinYark/Sdirt |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_11213 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Simulating Dual-Pixel Images From Ray Tracing For Depth Estimation He, Fengchen Zhao, Dayang Xu, Hao Quan, Tingwei Zeng, Shaoqun Computer Vision and Pattern Recognition Image and Video Processing Many studies utilize dual-pixel (DP) sensor phase characteristics for various applications, such as depth estimation and deblurring. However, since the DP image features are entirely determined by the camera hardware, DP-depth paired datasets are very scarce, especially when performing depth estimation on customized cameras. To overcome this, studies simulate DP images using ideal optical system models. However, these simulations often violate real optical propagation laws, leading to poor generalization to real DP data. To address this, we investigate the domain gap between simulated and real DP data, and propose solutions using the Simulating DP images from ray tracing (Sdirt) scheme. The Sdirt generates realistic DP images via ray tracing and integrates them into the depth estimation training pipeline. Experimental results show that models trained with Sdirt-simulated images generalize better to real DP data. The code and collected datasets will be available at github.com/LinYark/Sdirt |
| title | Simulating Dual-Pixel Images From Ray Tracing For Depth Estimation |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2503.11213 |