Dressi: A Hardware-Agnostic Differentiable Renderer with Reactive Shader Packing and Soft Rasterization

Simple item page
dc.contributor.authorTakimoto, Yusukeen_US
dc.contributor.authorSato, Hiroyukien_US
dc.contributor.authorTakehara, Hikarien_US
dc.contributor.authorUragaki, Keishiroen_US
dc.contributor.authorTawara, Takehiroen_US
dc.contributor.authorLiang, Xiaoen_US
dc.contributor.authorOku, Kentaroen_US
dc.contributor.authorKishimoto, Wataruen_US
dc.contributor.authorZheng, Boen_US
dc.contributor.editorChaine, Raphaëlleen_US
dc.contributor.editorKim, Min H.en_US
dc.date.accessioned2022-04-22T06:26:17Z
dc.date.available2022-04-22T06:26:17Z
dc.date.issued2022
dc.description.abstractDifferentiable rendering (DR) enables various computer graphics and computer vision applications through gradient-based optimization with derivatives of the rendering equation. Most rasterization-based approaches are built on general-purpose automatic differentiation (AD) libraries and DR-specific modules handcrafted using CUDA. Such a system design mixes DR algorithm implementation and algorithm building blocks, resulting in hardware dependency and limited performance. In this paper, we present a practical hardware-agnostic differentiable renderer called Dressi, which is based on a new full AD design. The DR algorithms of Dressi are fully written in our Vulkan-based AD for DR, Dressi-AD, which supports all primitive operations for DR. Dressi-AD and our inverse UV technique inside it bring hardware independence and acceleration by graphics hardware. Stage packing, our runtime optimization technique, can adapt hardware constraints and efficiently execute complex computational graphs of DR with reactive cache considering the render pass hierarchy of Vulkan. HardSoftRas, our novel rendering process, is designed for inverse rendering with a graphics pipeline. Under the limited functionalities of the graphics pipeline, HardSoftRas can propagate the gradients of pixels from the screen space to far-range triangle attributes. Our experiments and applications demonstrate that Dressi establishes hardware independence, high-quality and robust optimization with fast speed, and photorealistic rendering.en_US
dc.description.number2
dc.description.sectionheadersLearning for Rendering
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume41
dc.identifier.doi10.1111/cgf.14455
dc.identifier.issn1467-8659
dc.identifier.pages13-27
dc.identifier.pages15 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14455
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14455
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies --> Rasterization; Shape inference
dc.subjectComputing methodologies
dc.subjectRasterization
dc.subjectShape inference
dc.titleDressi: A Hardware-Agnostic Differentiable Renderer with Reactive Shader Packing and Soft Rasterizationen_US
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
v41i2pp013-027.pdf
Size:
19.12 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1042_3.mp4
Size:
50.46 MB
Format:
Unknown data format
Download
Thumbnail Image
Name:
paper1042_4.pdf
Size:
2.56 MB
Format:
Adobe Portable Document Format
Download
Collections
41-Issue 2