Video Frame Interpolation for High Dynamic Range Sequences Captured with Dual-exposure Sensors

Simple item page
dc.contributor.authorCogalan, Uguren_US
dc.contributor.authorBemana, Mojtabaen_US
dc.contributor.authorSeidel, Hans-Peteren_US
dc.contributor.authorMyszkowski, Karolen_US
dc.contributor.editorMyszkowski, Karolen_US
dc.contributor.editorNiessner, Matthiasen_US
dc.date.accessioned2023-05-03T06:09:46Z
dc.date.available2023-05-03T06:09:46Z
dc.date.issued2023
dc.description.abstractVideo frame interpolation (VFI) enables many important applications such as slow motion playback and frame rate conversion. However, one major challenge in using VFI is accurately handling high dynamic range (HDR) scenes with complex motion. To this end, we explore the possible advantages of dual-exposure sensors that readily provide sharp short and blurry long exposures that are spatially registered and whose ends are temporally aligned. This way, motion blur registers temporally continuous information on the scene motion that, combined with the sharp reference, enables more precise motion sampling within a single camera shot. We demonstrate that this facilitates a more complex motion reconstruction in the VFI task, as well as HDR frame reconstruction that so far has been considered only for the originally captured frames, not in-between interpolated frames. We design a neural network trained in these tasks that clearly outperforms existing solutions. We also propose a metric for scene motion complexity that provides important insights into the performance of VFI methods at test time.en_US
dc.description.number2
dc.description.sectionheadersImage and Video Processinng
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume42
dc.identifier.doi10.1111/cgf.14748
dc.identifier.issn1467-8659
dc.identifier.pages119-131
dc.identifier.pages13 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14748
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14748
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 processing
dc.subjectComputing methodologies
dc.subjectComputational photography
dc.subjectImage processing
dc.titleVideo Frame Interpolation for High Dynamic Range Sequences Captured with Dual-exposure Sensorsen_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
v42i2pp119-131_cgf14748.pdf
Size:
51.66 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1079_mm.mp4
Size:
95.56 MB
Format:
Unknown data format
Download
Collections
42-Issue 2