-
公开(公告)号：US10769848B1
公开(公告)日：2020-09-08
申请号：US16421729
申请日：2019-05-24
申请人： Adobe, Inc.
发明人： Oliver Wang , Vladimir Kim , Matthew Fisher , Elya Shechtman , Chen-Hsuan Lin , Bryan Russell
摘要： Techniques are disclosed for 3D object reconstruction using photometric mesh representations. A decoder is pretrained to transform points sampled from 2D patches of representative objects into 3D polygonal meshes. An image frame of the object is fed into an encoder to get an initial latent code vector. For each frame and camera pair from the sequence, a polygonal mesh is rendered at the given viewpoints. The mesh is optimized by creating a virtual viewpoint, rasterized to obtain a depth map. The 3D mesh projections are aligned by projecting the coordinates corresponding to the polygonal face vertices of the rasterized mesh to both selected viewpoints. The photometric error is determined from RGB pixel intensities sampled from both frames. Gradients from the photometric error are backpropagated into the vertices of the assigned polygonal indices by relating the barycentric coordinates of each image to update the latent code vector.
-
公开(公告)号：US20200302251A1
公开(公告)日：2020-09-24
申请号：US16897068
申请日：2020-06-09
申请人： Adobe Inc.
发明人： Elya Shechtman , Oliver Wang , Mehmet Yumer , Chen-Hsuan Lin
摘要： The present disclosure relates to an image composite system that employs a generative adversarial network to generate realistic composite images. For example, in one or more embodiments, the image composite system trains a geometric prediction neural network using an adversarial discrimination neural network to learn warp parameters that provide correct geometric alignment of foreground objects with respect to a background image. Once trained, the determined warp parameters provide realistic geometric corrections to foreground objects such that the warped foreground objects appear to blend into background images naturally when composited together.
-
公开(公告)号：US20190251401A1
公开(公告)日：2019-08-15
申请号：US15897910
申请日：2018-02-15
申请人： Adobe Inc.
发明人： Elya Shechtman , Oliver Wang , Mehmet Yumer , Chen-Hsuan Lin
摘要： The present disclosure relates to an image composite system that employs a generative adversarial network to generate realistic composite images. For example, in one or more embodiments, the image composite system trains a geometric prediction neural network using an adversarial discrimination neural network to learn warp parameters that provide correct geometric alignment of foreground objects with respect to a background image. Once trained, the determined warp parameters provide realistic geometric corrections to foreground objects such that the warped foreground objects appear to blend into background images naturally when composited together.
-
公开(公告)号：US20200372710A1
公开(公告)日：2020-11-26
申请号：US16985402
申请日：2020-08-05
申请人： Adobe, Inc.
发明人： Oliver Wang , Vladimir Kim , Matthew Fisher , Elya Shechtman , Chen-Hsuan Lin , Bryan Russell
摘要： Techniques are disclosed for 3D object reconstruction using photometric mesh representations. A decoder is pretrained to transform points sampled from 2D patches of representative objects into 3D polygonal meshes. An image frame of the object is fed into an encoder to get an initial latent code vector. For each frame and camera pair from the sequence, a polygonal mesh is rendered at the given viewpoints. The mesh is optimized by creating a virtual viewpoint, rasterized to obtain a depth map. The 3D mesh projections are aligned by projecting the coordinates corresponding to the polygonal face vertices of the rasterized mesh to both selected viewpoints. The photometric error is determined from RGB pixel intensities sampled from both frames. Gradients from the photometric error are backpropagated into the vertices of the assigned polygonal indices by relating the barycentric coordinates of each image to update the latent code vector.
-
公开(公告)号：US11328523B2
公开(公告)日：2022-05-10
申请号：US16897068
申请日：2020-06-09
申请人： Adobe Inc.
发明人： Elya Shechtman , Oliver Wang , Mehmet Yumer , Chen-Hsuan Lin
IPC分类号： G06V30/194 , G06N3/04 , G06N3/08
摘要： The present disclosure relates to an image composite system that employs a generative adversarial network to generate realistic composite images. For example, in one or more embodiments, the image composite system trains a geometric prediction neural network using an adversarial discrimination neural network to learn warp parameters that provide correct geometric alignment of foreground objects with respect to a background image. Once trained, the determined warp parameters provide realistic geometric corrections to foreground objects such that the warped foreground objects appear to blend into background images naturally when composited together.
-
公开(公告)号：US11189094B2
公开(公告)日：2021-11-30
申请号：US16985402
申请日：2020-08-05
申请人： Adobe, Inc.
发明人： Oliver Wang , Vladimir Kim , Matthew Fisher , Elya Shechtman , Chen-Hsuan Lin , Bryan Russell
摘要： Techniques are disclosed for 3D object reconstruction using photometric mesh representations. A decoder is pretrained to transform points sampled from 2D patches of representative objects into 3D polygonal meshes. An image frame of the object is fed into an encoder to get an initial latent code vector. For each frame and camera pair from the sequence, a polygonal mesh is rendered at the given viewpoints. The mesh is optimized by creating a virtual viewpoint, rasterized to obtain a depth map. The 3D mesh projections are aligned by projecting the coordinates corresponding to the polygonal face vertices of the rasterized mesh to both selected viewpoints. The photometric error is determined from RGB pixel intensities sampled from both frames. Gradients from the photometric error are backpropagated into the vertices of the assigned polygonal indices by relating the barycentric coordinates of each image to update the latent code vector.
-
公开(公告)号：US10719742B2
公开(公告)日：2020-07-21
申请号：US15897910
申请日：2018-02-15
申请人： Adobe Inc.
发明人： Elya Shechtman , Oliver Wang , Mehmet Yumer , Chen-Hsuan Lin
摘要： The present disclosure relates to an image composite system that employs a generative adversarial network to generate realistic composite images. For example, in one or more embodiments, the image composite system trains a geometric prediction neural network using an adversarial discrimination neural network to learn warp parameters that provide correct geometric alignment of foreground objects with respect to a background image. Once trained, the determined warp parameters provide realistic geometric corrections to foreground objects such that the warped foreground objects appear to blend into background images naturally when composited together.
-
-
-
-
-
-
搜索结果
7 条记录 (耗时 0.015 秒)
