Learning to Rasterize Differentiably
dc.contributor.author | Wu, Chenghao | en_US |
dc.contributor.author | Mailee, Hamila | en_US |
dc.contributor.author | Montazeri, Zahra | en_US |
dc.contributor.author | Ritschel, Tobias | en_US |
dc.contributor.editor | Garces, Elena | en_US |
dc.contributor.editor | Haines, Eric | en_US |
dc.date.accessioned | 2024-06-25T10:19:22Z | |
dc.date.available | 2024-06-25T10:19:22Z | |
dc.date.issued | 2024 | |
dc.description.abstract | Differentiable 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.number | 4 | |
dc.description.sectionheaders | Sampling | |
dc.description.seriesinformation | Computer Graphics Forum | |
dc.description.volume | 43 | |
dc.identifier.doi | 10.1111/cgf.15145 | |
dc.identifier.issn | 1467-8659 | |
dc.identifier.pages | 11 pages | |
dc.identifier.uri | https://doi.org/10.1111/cgf.15145 | |
dc.identifier.uri | https://diglib.eg.org/handle/10.1111/cgf15145 | |
dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
dc.subject | CCS Concepts: Computing methodologies → Rendering; Rasterization; Artificial intelligence | |
dc.subject | Computing methodologies → Rendering | |
dc.subject | Rasterization | |
dc.subject | Artificial intelligence | |
dc.title | Learning to Rasterize Differentiably | en_US |