GAMES Webinar 2024 – 352期(实时渲染技术) | 张嵩(犹他大学),鲁昊霖(加利福尼亚大学圣迭戈分校)
【GAMES Webinar 2024-352期】(渲染专题-实时渲染技术)
报告嘉宾:张嵩(犹他大学)
报告时间:2024年12月12号星期四下午2:00-2:40(北京时间)
报告题目:Area ReSTIR: Resampling for Real-Time Defocus and Antialiasing
报告摘要:
Recent advancements in spatiotemporal reservoir resampling (ReSTIR) leverage sample reuse from neighbors to efficiently evaluate the path integral. Like rasterization, ReSTIR methods implicitly assume a pinhole camera and evaluate the light arriving at a pixel through a single predetermined subpixel location at a time (e.g., the pixel center). This prevents efficient path reuse in and near pixels with high-frequency details. We introduce Area ReSTIR, extending ReSTIR reservoirs to also integrate each pixel’s 4D ray space, including 2D areas on the film and lens. We design novel subpixel-tracking temporal reuse and shift mappings that maximize resampling quality in such regions. This robustifies ReSTIR against high-frequency content, letting us importance sample subpixel and lens coordinates and efficiently render antialiasing and depth of field.
讲者简介:
张嵩,师从Dr. Cem Yuksel,目前是犹他大学计算机学院博士第三年。硕士也毕业于犹他大学。从事的方向是实时渲染,主要研究的问题聚焦于在多光源的场景下,如何通过样本重用来设计高效的实时路径追踪和阴影估计算法。
讲者主页:https://guiqi134.github.io/
报告嘉宾:鲁昊霖(加利福尼亚大学圣迭戈分校)
报告时间:2024年12月12号星期四下午2:40-3:00(北京时间)
报告题目:Real-Time Path Guiding Using Bounding Voxel Sampling
报告摘要:
We propose a real-time path guiding method, Voxel Path Guiding (VXPG), that significantly improves fitting efficiency under limited sampling budget. Our key idea is to use a spatial irradiance voxel data structure across all shading points to guide the location of path vertices. For each frame, we first populate the voxel data structure with irradiance and geometry information. To sample from the data structure for a shading point, we need to select a voxel with high contribution to that point. To importance sample the voxels while taking visibility into consideration, we adapt techniques from offline many-lights rendering by clustering pairs of shading points and voxels. Finally, we unbiasedly sample within the selected voxel while taking the geometry inside into consideration.
讲者简介:
鲁昊霖,硕士毕业于加利福尼亚大学圣迭戈分校,师从Prof. Tzu-Mao Li,目前是马克斯·普朗克计算机科学研究所研究实习生。研究兴趣是实时渲染,离线渲染与逆渲染。
讲者主页:https://suikasibyl.github.io/
主持人简介:
唐睿,群核科技首席科学家,杭州市“万人计划”特殊人才,现任杭州市经济和信息化局评审专家库专家,中国图学学会专业委员会委员,图形学与混合现实研讨会执行委员。师从浙江大学副校长陈刚教授与英国皇家工程院士Darren Cosker教授,长期从事计算机图形学、人工智能与具身智能感知领域工作。在ACM TOG,ECCV,CVPR,Siggraph, Sigraph Asia等国内外高水平学术会议和期刊发表论文20余篇,获中国和美国授权专利57项;担任ACM TOG、Nature子刊等计算机与人工智能领域期刊审稿人;主持/参与多项欧美、浙江省省级计算机图形技术相关科研与高新技术纵向、横向课题,总金额超2.6亿;2022年度浙江省省内首版次软件产品第一完成人。
GAMES主页的“使用教程”中有 “如何观看GAMES Webinar直播?”及“如何加入GAMES微信群?”的信息;
GAMES主页的“资源分享”有往届的直播讲座的视频及PPT等。
观看直播的链接:https://live.bilibili.com/h5/24617282