Learning to Rasterize Differentiably

dc.contributor.authorWu, Chenghaoen_US
dc.contributor.authorMailee, Hamilaen_US
dc.contributor.authorMontazeri, Zahraen_US
dc.contributor.authorRitschel, Tobiasen_US
dc.contributor.editorGarces, Elenaen_US
dc.contributor.editorHaines, Ericen_US
dc.date.accessioned2024-06-25T10:19:22Z
dc.date.available2024-06-25T10:19:22Z
dc.date.issued2024
dc.description.abstractDifferentiable rasterization changes the standard formulation of primitive rasterization -by enabling gradient flow from a pixel to its underlying triangles- using distribution functions in different stages of rendering, creating a ''soft'' version of the original rasterizer. However, choosing the optimal softening function that ensures the best performance and convergence to a desired goal requires trial and error. Previous work has analyzed and compared several combinations of softening. In this work, we take it a step further and, instead of making a combinatorial choice of softening operations, parameterize the continuous space of common softening operations. We study meta-learning tunable softness functions over a set of inverse rendering tasks (2D and 3D shape, pose and occlusion) so it generalizes to new and unseen differentiable rendering tasks with optimal softness.en_US
dc.description.number4
dc.description.sectionheadersSampling
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume43
dc.identifier.doi10.1111/cgf.15145
dc.identifier.issn1467-8659
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.15145
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf15145
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Rendering; Rasterization; Artificial intelligence
dc.subjectComputing methodologies → Rendering
dc.subjectRasterization
dc.subjectArtificial intelligence
dc.titleLearning to Rasterize Differentiablyen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
v43i4_01_cgf15145.pdf
Size:
11.09 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
paper1058.zip
Size:
135.53 MB
Format:
Zip file
Collections