Fitting Spherical Gaussians to Dynamic HDRI Sequences
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917862975733760 |
|---|---|
| author | Clausen, Pascal Ma, Li He, Mingming Tasel, Ahmet Levent Pilarski, Oliver Debevec, Paul |
| author_facet | Clausen, Pascal Ma, Li He, Mingming Tasel, Ahmet Levent Pilarski, Oliver Debevec, Paul |
| contents | We present a technique for fitting high dynamic range illumination (HDRI) sequences using anisotropic spherical Gaussians (ASGs) while preserving temporal consistency in the compressed HDRI maps. Our approach begins with an optimization network that iteratively minimizes a composite loss function, which includes both reconstruction and diffuse losses. This allows us to represent all-frequency signals with a small number of ASGs, optimizing their directions, sharpness, and intensity simultaneously for an individual HDRI. To extend this optimization into the temporal domain, we introduce a temporal consistency loss, ensuring a consistent approximation across the entire HDRI sequence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_06511 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fitting Spherical Gaussians to Dynamic HDRI Sequences Clausen, Pascal Ma, Li He, Mingming Tasel, Ahmet Levent Pilarski, Oliver Debevec, Paul Computer Vision and Pattern Recognition Graphics We present a technique for fitting high dynamic range illumination (HDRI) sequences using anisotropic spherical Gaussians (ASGs) while preserving temporal consistency in the compressed HDRI maps. Our approach begins with an optimization network that iteratively minimizes a composite loss function, which includes both reconstruction and diffuse losses. This allows us to represent all-frequency signals with a small number of ASGs, optimizing their directions, sharpness, and intensity simultaneously for an individual HDRI. To extend this optimization into the temporal domain, we introduce a temporal consistency loss, ensuring a consistent approximation across the entire HDRI sequence. |
| title | Fitting Spherical Gaussians to Dynamic HDRI Sequences |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2412.06511 |