-
公开(公告)号:US20240112356A1
公开(公告)日:2024-04-04
申请号:US17957423
申请日:2022-09-30
Applicant: Nvidia Corporation
Inventor: Karthick Sekkappan , Aurobinda Maharana , Vipul Parashar
IPC: G06T7/269 , G06V10/25 , G06V10/26 , H04N19/132 , H04N19/139 , H04N19/513
CPC classification number: G06T7/269 , G06V10/25 , G06V10/26 , H04N19/132 , H04N19/139 , H04N19/513
Abstract: Systems and methods estimate optical flow vectors for occluded pixels between frames of a video sequence. Regions of occluded pixels may be identified and a cause of their occlusion may be determined. Different estimation techniques may be applied based, at least in part, on the cause of occlusion to provide a lightweight, less resource intensive estimation of optical flow data. Optical flow vectors for pixels that are occluded due to movement out of a frame may be estimated using a first technique while optical flow vectors for pixels that are occluded due to foreground movement may be estimated using a second technique.
-
2.
公开(公告)号:US20240127572A1
公开(公告)日:2024-04-18
申请号:US17968260
申请日:2022-10-18
Applicant: Nvidia Corporation
Inventor: Karthick Sekkappan , Aurobinda Maharana
IPC: G06V10/26 , G06T7/269 , G06V10/56 , G06V10/60 , H04N19/139
CPC classification number: G06V10/26 , G06T7/269 , G06V10/56 , G06V10/60 , H04N19/139 , G06T2207/10016 , G06T2207/20032
Abstract: Systems and methods estimate occluded pixels in frames of a video sequence. Optical flow data is received to determine a validity for forward and backward flow vectors for a common pixel location in a first frame and a second frame that are temporally next to one another. Occlusion information for the first frame determines pixels that are hidden in the second frame with respect to playback from the first frame to the second frame. Occlusion information for the second frame determines pixels that are hidden in the first frame with respect to playback from the second frame to the first frame.
-
公开(公告)号:US12229970B2
公开(公告)日:2025-02-18
申请号:US17888185
申请日:2022-08-15
Applicant: NVIDIA Corporation
Inventor: Aurobinda Maharana , Karthick Sekkappan , Rohit Naskulwar
Abstract: In examples, when attempting to interpolate or extrapolate a frame based on motion vectors of two adjacent frames, there can be more than one pixel value mapped to a given location in the frame. To select between conflicting pixel values for the given location, similarities between the motion vectors of source pixels that cause the conflict and global flow may be evaluated. For example, a level of similarity for a motion vector may be computed using a similarity metric based at least on a difference between an angle of a global motion vector and an angle of the motion vector. The similarity metric may also be based at least on a difference between a magnitude of the global motion vector and a magnitude of the motion vector. The similarity metric may weigh the difference between the angles in proportion to the magnitude of the global motion vector.
-
公开(公告)号:US20240054657A1
公开(公告)日:2024-02-15
申请号:US17888185
申请日:2022-08-15
Applicant: NVIDIA Corporation
Inventor: Aurobinda Maharana , Karthick Sekkappan , Rohit Naskulwar
Abstract: In examples, when attempting to interpolate or extrapolate a frame based on motion vectors of two adjacent frames, there can be more than one pixel value mapped to a given location in the frame. To select between conflicting pixel values for the given location, similarities between the motion vectors of source pixels that cause the conflict and global flow may be evaluated. For example, a level of similarity for a motion vector may be computed using a similarity metric based at least on a difference between an angle of a global motion vector and an angle of the motion vector. The similarity metric may also be based at least on a difference between a magnitude of the global motion vector and a magnitude of the motion vector. The similarity metric may weigh the difference between the angles in proportion to the magnitude of the global motion vector.
-
-
-