We present a novel real-time image-based rendering system for generating realistic novel views of complex scenes from a set of uncalibrated images. A combination of structure-and-motion and stereo techniques is used to obtain calibrated cameras and dense depth maps for all recorded images. These depth maps are converted into restrictive quadtrees, which allow for adaptive, view-dependent tessellations while storing per-vertex quality. When rendering a novel view, a subset of suitable cameras is selected based upon a ranking criterion. In the spirit of the unstructured lumigraph rendering approach a blending field is evaluated, although the implementation is adapted on several points. We alleviate the need for the creation of a geometric proxy for each novel view while the camera blending field is sampled in a more optimal, non-uniform way and combined with the per-vertex quality to reduce texture artifacts. In order to make real-time visualization possible, all critical steps of the visualization pipeline are programmed in a highly optimized way on commodity graphics hardware using the OpenGL Shading Language. The proposed system can handle complex scenes such as large outdoor scenes as well as small objects with a large number of acquired images.
{"title":"Real-time image based rendering from uncalibrated images","authors":"Geert Willems, F. Verbiest, M. Vergauwen, L. Gool","doi":"10.1109/3DIM.2005.66","DOIUrl":"https://doi.org/10.1109/3DIM.2005.66","url":null,"abstract":"We present a novel real-time image-based rendering system for generating realistic novel views of complex scenes from a set of uncalibrated images. A combination of structure-and-motion and stereo techniques is used to obtain calibrated cameras and dense depth maps for all recorded images. These depth maps are converted into restrictive quadtrees, which allow for adaptive, view-dependent tessellations while storing per-vertex quality. When rendering a novel view, a subset of suitable cameras is selected based upon a ranking criterion. In the spirit of the unstructured lumigraph rendering approach a blending field is evaluated, although the implementation is adapted on several points. We alleviate the need for the creation of a geometric proxy for each novel view while the camera blending field is sampled in a more optimal, non-uniform way and combined with the per-vertex quality to reduce texture artifacts. In order to make real-time visualization possible, all critical steps of the visualization pipeline are programmed in a highly optimized way on commodity graphics hardware using the OpenGL Shading Language. The proposed system can handle complex scenes such as large outdoor scenes as well as small objects with a large number of acquired images.","PeriodicalId":170883,"journal":{"name":"Fifth International Conference on 3-D Digital Imaging and Modeling (3DIM'05)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129071886","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}
We compare two transform-based indexing methods for retrieval of 3D objects. We apply 3D discrete Fourier transform (DFT) and 3D radial cosine transform (RCT) to the voxelized data of 3D objects. Rotation invariant features are derived from the coefficients of these transforms. Furthermore we compare two different voxel representations, namely, binary denoting object and background space, and continuous after distance transformation. In the binary voxel representation the voxel values are simply set to 1 on the surface of the object and 0 elsewhere. In the continuous-valued representation the space is filled with a function of distance transform. The rotation invariance properties of the DFT and RCT schemes are analyzed. We have conducted retrieval experiments on the Princeton Shape Benchmark and investigated the retrieval performance of the methods using several quality measures.
{"title":"Transform-based methods for indexing and retrieval of 3D objects","authors":"H. Dutagaci, B. Sankur, Y. Yemez","doi":"10.1109/3DIM.2005.79","DOIUrl":"https://doi.org/10.1109/3DIM.2005.79","url":null,"abstract":"We compare two transform-based indexing methods for retrieval of 3D objects. We apply 3D discrete Fourier transform (DFT) and 3D radial cosine transform (RCT) to the voxelized data of 3D objects. Rotation invariant features are derived from the coefficients of these transforms. Furthermore we compare two different voxel representations, namely, binary denoting object and background space, and continuous after distance transformation. In the binary voxel representation the voxel values are simply set to 1 on the surface of the object and 0 elsewhere. In the continuous-valued representation the space is filled with a function of distance transform. The rotation invariance properties of the DFT and RCT schemes are analyzed. We have conducted retrieval experiments on the Princeton Shape Benchmark and investigated the retrieval performance of the methods using several quality measures.","PeriodicalId":170883,"journal":{"name":"Fifth International Conference on 3-D Digital Imaging and Modeling (3DIM'05)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116810911","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：