Ya-Chuan Hsu, Matthew C. Fontaine, Sam Earle, Maria Edwards, J. Togelius, S. Nikolaidis
{"title":"Generating Diverse Indoor Furniture Arrangements","authors":"Ya-Chuan Hsu, Matthew C. Fontaine, Sam Earle, Maria Edwards, J. Togelius, S. Nikolaidis","doi":"10.1145/3532719.3543244","DOIUrl":"https://doi.org/10.1145/3532719.3543244","url":null,"abstract":"We present a method for generating arrangements of indoor furniture from human-designed furniture layout data. Our method creates arrangements that target specified diversity, such as the total price of all furniture in the room and the number of pieces placed. To generate realistic furniture arrangement, we train a generative adversarial network (GAN) on human-designed layouts. To target specific diversity in the arrangements, we optimize the latent space of the GAN via a quality diversity algorithm to generate a diverse arrangement collection. Experiments show our approach discovers a set of arrangements that are similar to human-designed layouts but varies in price and number of furniture pieces.","PeriodicalId":289790,"journal":{"name":"ACM SIGGRAPH 2022 Posters","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116140560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"HDR Lighting Dilation for Dynamic Range Reduction on Virtual Production Stages","authors":"P. Debevec, Chloe LeGendre","doi":"10.1145/3532719.3543243","DOIUrl":"https://doi.org/10.1145/3532719.3543243","url":null,"abstract":"We present a technique to reduce the dynamic range of an HDRI lighting environment map in an efficient, energy-preserving manner by spreading out the light of concentrated light sources. This allows us to display a reasonable approximation of the illumination of an HDRI map in a lighting reproduction system with limited dynamic range such as virtual production LED Stage. The technique identifies regions of the HDRI map above a given pixel threshold, dilates these regions until the average pixel value within each is below the threshold, and finally replaces each dilated region’s pixels with the region’s average pixel value. The new HDRI map contains the same energy as the original, spreads the light as little as possible, and avoids chromatic fringing.","PeriodicalId":289790,"journal":{"name":"ACM SIGGRAPH 2022 Posters","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125436518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Manos N. Kamarianakis, Ilias Chrysovergis, Mike Kentros, G. Papagiannakis
{"title":"Recording and replaying psychomotor user actions in VR","authors":"Manos N. Kamarianakis, Ilias Chrysovergis, Mike Kentros, G. Papagiannakis","doi":"10.1145/3532719.3543253","DOIUrl":"https://doi.org/10.1145/3532719.3543253","url":null,"abstract":"We introduce a novel method that describes the functionality and characteristics of an efficient VR recorder with replay capabilities, implemented in a modern game engine, publicly available for free.","PeriodicalId":289790,"journal":{"name":"ACM SIGGRAPH 2022 Posters","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128695275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Evaluating the Quality of a Synthesized Motion with the Fréchet Motion Distance","authors":"Antoine Maiorca, Youngwoo Yoon, T. Dutoit","doi":"10.1145/3532719.3543228","DOIUrl":"https://doi.org/10.1145/3532719.3543228","url":null,"abstract":"Figure 1: Overview of the FMD metric. During training process, the autoencoder learns a compressed motion feature space z by reconstructing the input motion. Then, the encoder computes the latent space from the ground truth and synthetic motion dataset. Finally, the Fréchet distance is measured between the two latent spaces to evaluate the quality and diversity of the motion samples from the synthetic dataset.","PeriodicalId":289790,"journal":{"name":"ACM SIGGRAPH 2022 Posters","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128464861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}