Cinematic Gaussians: Real-Time HDR Radiance Fields with Depth of Field
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917844627750912 |
|---|---|
| author | Wang, Chao Wolski, Krzysztof Kerbl, Bernhard Serrano, Ana Bemana, Mojtaba Seidel, Hans-Peter Myszkowski, Karol Leimkühler, Thomas |
| author_facet | Wang, Chao Wolski, Krzysztof Kerbl, Bernhard Serrano, Ana Bemana, Mojtaba Seidel, Hans-Peter Myszkowski, Karol Leimkühler, Thomas |
| contents | Radiance field methods represent the state of the art in reconstructing complex scenes from multi-view photos. However, these reconstructions often suffer from one or both of the following limitations: First, they typically represent scenes in low dynamic range (LDR), which restricts their use to evenly lit environments and hinders immersive viewing experiences. Secondly, their reliance on a pinhole camera model, assuming all scene elements are in focus in the input images, presents practical challenges and complicates refocusing during novel-view synthesis. Addressing these limitations, we present a lightweight method based on 3D Gaussian Splatting that utilizes multi-view LDR images of a scene with varying exposure times, apertures, and focus distances as input to reconstruct a high-dynamic-range (HDR) radiance field. By incorporating analytical convolutions of Gaussians based on a thin-lens camera model as well as a tonemapping module, our reconstructions enable the rendering of HDR content with flexible refocusing capabilities. We demonstrate that our combined treatment of HDR and depth of field facilitates real-time cinematic rendering, outperforming the state of the art. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_07329 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cinematic Gaussians: Real-Time HDR Radiance Fields with Depth of Field Wang, Chao Wolski, Krzysztof Kerbl, Bernhard Serrano, Ana Bemana, Mojtaba Seidel, Hans-Peter Myszkowski, Karol Leimkühler, Thomas Computer Vision and Pattern Recognition Image and Video Processing Radiance field methods represent the state of the art in reconstructing complex scenes from multi-view photos. However, these reconstructions often suffer from one or both of the following limitations: First, they typically represent scenes in low dynamic range (LDR), which restricts their use to evenly lit environments and hinders immersive viewing experiences. Secondly, their reliance on a pinhole camera model, assuming all scene elements are in focus in the input images, presents practical challenges and complicates refocusing during novel-view synthesis. Addressing these limitations, we present a lightweight method based on 3D Gaussian Splatting that utilizes multi-view LDR images of a scene with varying exposure times, apertures, and focus distances as input to reconstruct a high-dynamic-range (HDR) radiance field. By incorporating analytical convolutions of Gaussians based on a thin-lens camera model as well as a tonemapping module, our reconstructions enable the rendering of HDR content with flexible refocusing capabilities. We demonstrate that our combined treatment of HDR and depth of field facilitates real-time cinematic rendering, outperforming the state of the art. |
| title | Cinematic Gaussians: Real-Time HDR Radiance Fields with Depth of Field |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2406.07329 |