A Post Processing Technique to Automatically Remove Floater Artifacts in Neural Radiance Fields

Simple item page
dc.contributor.authorWirth, Tristanen_US
dc.contributor.authorRak, Arneen_US
dc.contributor.authorKnauthe, Volkeren_US
dc.contributor.authorFellner, Dieter W.en_US
dc.contributor.editorChaine, Raphaëlleen_US
dc.contributor.editorDeng, Zhigangen_US
dc.contributor.editorKim, Min H.en_US
dc.date.accessioned2023-10-09T07:37:33Z
dc.date.available2023-10-09T07:37:33Z
dc.date.issued2023
dc.description.abstractNeural Radiance Fields have revolutionized Novel View Synthesis by providing impressive levels of realism. However, in most in-the-wild scenes they suffer from floater artifacts that occur due to sparse input images or strong view-dependent effects. We propose an approach that uses neighborhood based clustering and a consistency metric on NeRF models trained on different scene scales to identify regions that contain floater artifacts based on Instant-NGPs multiscale occupancy grids. These occupancy grids contain the position of relevant optical densities in the scene. By pruning the regions that we identified as containing floater artifacts, they are omitted during the rendering process, leading to higher quality resulting images. Our approach has no negative runtime implications for the rendering process and does not require retraining of the underlying Multi Layer Perceptron. We show on a qualitative base, that our approach is suited to remove floater artifacts while preserving most of the scenes relevant geometry. Furthermore, we conduct a comparison to state-of-the-art techniques on the Nerfbusters dataset, that was created with measuring the implications of floater artifacts in mind. This comparison shows, that our method outperforms currently available techniques. Our approach does not require additional user input, but can be be used in an interactive manner. In general, the presented approach is applicable to every architecture that uses an explicit representation of a scene's occupancy distribution to accelerate the rendering process.en_US
dc.description.number7
dc.description.sectionheadersLearning and Image Processing
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume42
dc.identifier.doi10.1111/cgf.14977
dc.identifier.issn1467-8659
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14977
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14977
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.titleA Post Processing Technique to Automatically Remove Floater Artifacts in Neural Radiance Fieldsen_US
Files
Original bundle
Now showing 1 - 5 of 5
No Thumbnail Available
Name:
v42i7_49_14977.pdf
Size:
21.79 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1156_mm_1.mp4
Size:
7.06 MB
Format:
Unknown data format
Download
No Thumbnail Available
Name:
paper1156_mm_2.mp4
Size:
7.56 MB
Format:
Unknown data format
Download
No Thumbnail Available
Name:
paper1156_mm_1.mp4
Size:
7.06 MB
Format:
Unknown data format
Download
No Thumbnail Available
Name:
paper1156_mm_2.mp4
Size:
7.56 MB
Format:
Unknown data format
Download
Collections
42-Issue 7