BEGIN:VCALENDAR VERSION:2.0 PRODID:Linklings LLC BEGIN:VTIMEZONE TZID:Asia/Seoul X-LIC-LOCATION:Asia/Seoul BEGIN:STANDARD TZOFFSETFROM:+0900 TZOFFSETTO:+0900 TZNAME:KST DTSTART:18871231T000000 DTSTART:19881009T020000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20230103T035346Z LOCATION:Room 324\, Level 3\, West Wing DTSTART;TZID=Asia/Seoul:20221206T153000 DTEND;TZID=Asia/Seoul:20221206T170000 UID:siggraphasia_SIGGRAPH Asia 2022_sess155@linklings.com SUMMARY:Differentiable Rendering DESCRIPTION:Technical Communications, Technical Papers\n\nThe presentation s will be followed by a 30-min Interactive Discussion Session at Room 325- CD.\n\nThe Technical Papers program is the premier international forum for disseminating new scholarly work in computer graphics and interactive tec hniques. Technical Papers are published as a special issue of ACM Transact ions on Graphics. In addition to papers selected by the SIGGRAPH Asia 2022 Technical Papers Jury, the conference presents papers that have been publ ished in ACM Transactions on Graphics during the past year. Accepted paper s adhere to the highest scientific standards.\n\nThe Technical Communicati ons program is a premier forum for presenting the latest developments and research still in progress. Leading international experts in academia and industry present work that showcase actual implementations of research ide as, works at the crossroads of computer graphics with computer vision, mac hine learning, HCI, VR, CAD, visualization, and many others\n\nEfficient D ifferentiation of Pixel Reconstruction Filters for Path-Space Differentiab le Rendering\n\nYu, Zhang, Dong, Nowrouzezahrai, Zhao\n\nPixel reconstruct ion filters play an important role in physics-based rendering and have bee n thoroughly studied. In physics-based differentiable rendering, however, the proper treatment of pixel reconstruction filters has remained largely under-explored. We present a new technique to efficiently dif...\n\n------ ---------------\nDepth of Field Aware Differentiable Rendering\n\nPidhorsk yi, Bagautdinov, Ma, Saragih, Schwartz...\n\nCameras with a finite apertur e diameter exhibit defocus for scene elements that are not at the focus di stance and have only a limited depth of field within which objects appear acceptably sharp. In this work, we address the problem of applying inverse rendering techniques to input data that exhibits...\n\n------------------ ---\nLearning-based Inverse Rendering of Complex Indoor Scenes with Differ entiable Monte Carlo Raytracing\n\nZhu, Luan, Huo, Lin, Zhong...\n\nIndoor scenes typically exhibit complex, spatially-varying appearance from globa l illumination, making the inverse rendering a challenging ill-posed probl em. This work presents an end-to-end, learning-based inverse rendering fra mework incorporating differentiable Monte Carlo raytracing with importan.. .\n\n---------------------\nOptical Parameter Estimation for Hair and Fur using Differentiable Rendering\n\nShibaike, Iwasaki\n\nWe propose a parame ter estimation method of Bidirectional Curve Scattering Distribution Funct ion for hair and fur using differentiable rendering.\n\n------------------ ---\nDifferentiable Point-Based Radiance Fields for Efficient View Synthes is\n\nZhang, Baek, Rusinkiewicz, Heide\n\nWe propose a differentiable rend ering algorithm for efficient novel view synthesis. By departing from volu me-based representations in favor of a learned point representation, we im prove on existing methods more than an order of magnitude in memory and ru ntime, both in training and inference. The met...\n\n--------------------- \nDifferentiable Rendering of Neural SDFs through Reparameterization\n\nBa ngaru, Gharbi, Luan, Li, Sunkavalli...\n\nWe present a method to automatic ally compute correct gradients with respect to geometric scene parameters in neural SDF renderers. Recent physically-based differentiable rendering techniques for meshes have used edge-sampling to handle discontinuities, p articularly at object silhouettes, but SDFs do...\n\n--------------------- \nDifferentiable rendering using RGBXY derivatives and optimal transport\n \nXing, Luan, Yan, Hu, Qian...\n\nWe present a novel differentiable render ing framework that is reformulated from the Lagrangian view. Inspired by f luid simulation, traditional differentiable rendering approach can be view ed as the Eulerian method due to the fact that image derivatives are compu ted locally on a fixed grid of screen-...\n\n\nRegistration Category: FULL ACCESS, ON-DEMAND ACCESS\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON, ON-DE MAND END:VEVENT END:VCALENDAR