Deep Reconstruction of 3D Smoke Densities from Artist Sketches

Simple item page
dc.contributor.authorKim, Byungsooen_US
dc.contributor.authorHuang, Xingchangen_US
dc.contributor.authorWuelfroth, Lauraen_US
dc.contributor.authorTang, Jingweien_US
dc.contributor.authorCordonnier, Guillaumeen_US
dc.contributor.authorGross, Markusen_US
dc.contributor.authorSolenthaler, Barbaraen_US
dc.contributor.editorChaine, Raphaëlleen_US
dc.contributor.editorKim, Min H.en_US
dc.date.accessioned2022-04-22T06:27:03Z
dc.date.available2022-04-22T06:27:03Z
dc.date.issued2022
dc.description.abstractCreative processes of artists often start with hand-drawn sketches illustrating an object. Pre-visualizing these keyframes is especially challenging when applied to volumetric materials such as smoke. The authored 3D density volumes must capture realistic flow details and turbulent structures, which is highly non-trivial and remains a manual and time-consuming process. We therefore present a method to compute a 3D smoke density field directly from 2D artist sketches, bridging the gap between early-stage prototyping of smoke keyframes and pre-visualization. From the sketch inputs, we compute an initial volume estimate and optimize the density iteratively with an updater CNN. Our differentiable sketcher is embedded into the end-to-end training, which results in robust reconstructions. Our training data set and sketch augmentation strategy are designed such that it enables general applicability. We evaluate the method on synthetic inputs and sketches from artists depicting both realistic smoke volumes and highly non-physical smoke shapes. The high computational performance and robustness of our method at test time allows interactive authoring sessions of volumetric density fields for rapid prototyping of ideas by novice users.en_US
dc.description.number2
dc.description.sectionheadersModeling and Editing I
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume41
dc.identifier.doi10.1111/cgf.14461
dc.identifier.issn1467-8659
dc.identifier.pages97-110
dc.identifier.pages14 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14461
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14461
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies --> Shape modeling; Neural networks
dc.subjectComputing methodologies
dc.subjectShape modeling
dc.subjectNeural networks
dc.titleDeep Reconstruction of 3D Smoke Densities from Artist Sketchesen_US
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
v41i2pp097-110.pdf
Size:
22.17 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
eg22_sketch2fluid_crc_supp.mp4
Size:
135.35 MB
Format:
Unknown data format
Download
Thumbnail Image
Name:
eg22_sketch2fluid_crc_supp.pdf
Size:
23.84 MB
Format:
Adobe Portable Document Format
Download
Collections
41-Issue 2