Tsukasa Takeda, Shugo Yamaguchi, Kazuhito Sato, Kosuke Fukazawa, S. Morishima
{"title":"使用相机姿态插值和光度束调整的NeRF高效三维重建","authors":"Tsukasa Takeda, Shugo Yamaguchi, Kazuhito Sato, Kosuke Fukazawa, S. Morishima","doi":"10.1145/3588028.3603691","DOIUrl":null,"url":null,"abstract":"Figure 1: Comparison of the results of learning NeRF with the full camera poses and the interpolated-poses. The Full-Pose result uses the camera poses obtained by COLMAP with all the input images. The Interpolated-Pose result uses the poses obtained by COLMAP with several images and the interpolated poses between them as the initial poses. We apply Catmull-Rom Spline interpolation for translations and SLERP interpolation for rotations. The figure on the right shows the visualization of the camera poses using synthetic data. Interpolated-Pose generates images with almost the same quality as Full Pose.","PeriodicalId":113397,"journal":{"name":"ACM SIGGRAPH 2023 Posters","volume":"84 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Efficient 3D Reconstruction of NeRF using Camera Pose Interpolation and Photometric Bundle Adjustment\",\"authors\":\"Tsukasa Takeda, Shugo Yamaguchi, Kazuhito Sato, Kosuke Fukazawa, S. Morishima\",\"doi\":\"10.1145/3588028.3603691\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Figure 1: Comparison of the results of learning NeRF with the full camera poses and the interpolated-poses. The Full-Pose result uses the camera poses obtained by COLMAP with all the input images. The Interpolated-Pose result uses the poses obtained by COLMAP with several images and the interpolated poses between them as the initial poses. We apply Catmull-Rom Spline interpolation for translations and SLERP interpolation for rotations. The figure on the right shows the visualization of the camera poses using synthetic data. Interpolated-Pose generates images with almost the same quality as Full Pose.\",\"PeriodicalId\":113397,\"journal\":{\"name\":\"ACM SIGGRAPH 2023 Posters\",\"volume\":\"84 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-07-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACM SIGGRAPH 2023 Posters\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3588028.3603691\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM SIGGRAPH 2023 Posters","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3588028.3603691","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Efficient 3D Reconstruction of NeRF using Camera Pose Interpolation and Photometric Bundle Adjustment
Figure 1: Comparison of the results of learning NeRF with the full camera poses and the interpolated-poses. The Full-Pose result uses the camera poses obtained by COLMAP with all the input images. The Interpolated-Pose result uses the poses obtained by COLMAP with several images and the interpolated poses between them as the initial poses. We apply Catmull-Rom Spline interpolation for translations and SLERP interpolation for rotations. The figure on the right shows the visualization of the camera poses using synthetic data. Interpolated-Pose generates images with almost the same quality as Full Pose.