BEGIN:VCALENDAR VERSION:2.0 PRODID:Linklings LLC BEGIN:VTIMEZONE TZID:Asia/Tokyo X-LIC-LOCATION:Asia/Tokyo BEGIN:STANDARD TZOFFSETFROM:+0900 TZOFFSETTO:+0900 TZNAME:JST DTSTART:18871231T000000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250110T023309Z LOCATION:Hall B5 (1)\, B Block\, Level 5 DTSTART;TZID=Asia/Tokyo:20241203T144500 DTEND;TZID=Asia/Tokyo:20241203T155500 UID:siggraphasia_SIGGRAPH Asia 2024_sess106@linklings.com SUMMARY:Modeling and PDEs DESCRIPTION:Technical Papers\n\nEach Paper gives a 10 minute presentation. \n\nProjected Walk on Spheres: A Monte Carlo Closest Point Method for Surf ace PDEs\n\nWe present projected walk on spheres (PWoS), a novel pointwise and discretization-free Monte Carlo solver for surface PDEs with Dirichle t boundaries, as a generalization of the walk on spheres method (WoS) [Mu ller 1956; Sawhney and Crane 2020]. We adapt the recursive relationship of WoS designed fo...\n\n\nRyusuke Sugimoto, Nathan King, Toshiya Hachisuka, and Christopher Batty (University of Waterloo)\n---------------------\nTe xt-guided Controllable Mesh Refinement for Interactive 3D Modeling\n\nWe p ropose a novel technique for adding geometric details to an input coarse 3 D mesh guided by a text prompt. Our method is composed of three stages. Fi rst, we generate a single-view RGB image conditioned on the input coarse g eometry and the input text prompt. This single-view image generation step ...\n\n\nYun-Chun Chen and Selena Ling (University of Toronto); Zhiqin Che n, Vladimir G. Kim, and Matheus Gadelha (Adobe Research); and Alec Jacobso n (University of Toronto)\n---------------------\nSolving Inverse PDE Prob lems using Grid-Free Monte Carlo Estimators\n\nPartial differential equati ons can model diverse physical phenomena including heat diffusion, incompr essible flows, and electrostatic potentials. Given a description of an obj ect's boundary and interior, traditional methods solve such PDEs by densel y meshing the interior and then solving a large and...\n\n\nEkrem Fatih Yi lmazer (EPFL), Delio Vicini (Google Inc.), and Wenzel Jakob (EPFL)\n------ ---------------\nI❤️MESH: A DSL for Mesh Processing\n\nMesh processing alg orithms are often communicated via concise mathematical notation (e.g., su mmation over mesh neighborhoods). However, conversion of notation into wor king code remains a time-consuming and error-prone process, which requires arcane knowledge of low-level data structures and librarie...\n\n\nYong L i (South China University of Technology, George Mason University); Shoaib Kamil (Adobe Research); Keenan Crane (Carnegie Mellon University); Alec Ja cobson (University of Toronto, Adobe Research); and Yotam Gingold (George Mason University)\n---------------------\nDifferential Walk on Spheres\n\n We introduce a Monte Carlo method for computing derivatives of the solutio n to a partial differential equation (PDE) with respect to problem paramet ers (such as domain geometry or boundary conditions). Derivatives can be e valuated at arbitrary points, without performing a global solve or constru ctin...\n\n\nBailey Miller (Carnegie Mellon Uniersity), Rohan Sawhney (NVI DIA), and Keenan Crane and Ioannis Gkioulekas (Carnegie Mellon Uniersity)\ n---------------------\nDiffCSG: Differentiable CSG via Rasterization\n\nD ifferentiable rendering is a key ingredient for inverse rendering and mach ine learning, as it allows to optimize scene parameters (shape, materials, lighting) to best fit target images. Differentiable rendering requires th at each scene parameter relates to pixel values through differentiable ope rat...\n\n\nHaocheng Yuan (University of Edinburgh); Adrien Bousseau (Inri a Sophia-Antipolis, Université Côte d’Azur); Hao Pan (Microsoft Research A sia); Quancheng Zhang (Nanjing University); Niloy J. Mitra (University Col lege London (UCL), Adobe Research); and Changjian Li (University of Edinbu rgh)\n\nRegistration Category: Full Access, Full Access Supporter\n\nLangu age Format: English Language\n\nSession Chair: Yonghao Yue (Aoyama Gakuin University) END:VEVENT END:VCALENDAR