Cinematic Gaussians: Real-Time HDR Radiance Fields with Depth of Field

Simple item page
dc.contributor.authorWang, Chaoen_US
dc.contributor.authorWolski, Krzysztofen_US
dc.contributor.authorKerbl, Bernharden_US
dc.contributor.authorSerrano, Anaen_US
dc.contributor.authorBemama, Mojtabaen_US
dc.contributor.authorSeidel, Hans-Peteren_US
dc.contributor.authorMyszkowski, Karolen_US
dc.contributor.authorLeimkühler, Thomasen_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:07:42Z
dc.date.available2024-10-13T18:07:42Z
dc.date.issued2024
dc.description.abstractRadiance 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.en_US
dc.description.number7
dc.description.sectionheaders3D Reconstruction and Novel View Synthesis II
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume43
dc.identifier.doi10.1111/cgf.15214
dc.identifier.issn1467-8659
dc.identifier.pages13 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.15214
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf15214
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectCCS Concepts: Computing methodologies → Computational photography; Image-based rendering
dc.subjectComputing methodologies → Computational photography
dc.subjectImage
dc.subjectbased rendering
dc.titleCinematic Gaussians: Real-Time HDR Radiance Fields with Depth of Fielden_US
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
cgf15214.pdf
Size:
39.14 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1098_mm.pdf
Size:
107.48 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1098_mm.mp4
Size:
419.28 MB
Format:
Video MP4
Download
Collections
43-Issue 7