公开(公告)号：EP4432227A1

公开(公告)日：2024-09-18

申请号：EP23214854.4

申请日：2023-12-07

申请人： INTEL Corporation

发明人： Iyer, Darshan R. ,  Vembar, Deepak ,  Wang, Changliang ,  Bhatia, Sumit

IPC分类号： G06T7/269 ,  G06T1/20 ,  G06T3/4046 ,  G06T3/4053 ,  G06T5/60 ,  G06T5/70

CPC分类号： G06T7/269 ,  G06T2207/2008420130101 ,  G06T2207/2008120130101 ,  G06T3/4046 ,  G06T3/4053 ,  G06T5/70 ,  G06T5/60 ,  G06T2207/1002420130101 ,  G06T1/20

摘要： Described herein are techniques to enhance the user experience for 3D rendered applications via neural frame generation using upsampled optical flow data. In one embodiment, a neural network is trained using both sparse optical flow data and dense optical flow data to enable neural frame generation to be performed by a deployed neural network using only sparse optical flow data. The sparse optical flow data can be upsampled to dense optical flow data by the trained neural network. The neural network can then use the upsampled dense optical flow data to perform frame generation.

公开(公告)号：EP4428823A1

公开(公告)日：2024-09-11

申请号：EP23214773.6

申请日：2023-12-06

申请人： INTEL Corporation

发明人： Iyer, Darshan R. ,  Vembar, Deepak

IPC分类号： G06T15/00

CPC分类号： G06T15/005

摘要： Described herein are techniques to enhance the user experience for 3D rendered applications via neural frame generation and neural supersampling. One embodiment provides a latency aware unified neural network for frame interpolation and extrapolation. This unified neural network merges interpolation and extrapolation networks into one generalized network that can be applied to both interpolation and extrapolation, depending on the acceptable latency of performance. A further embodiment provides hardware-efficient and latency-aware spatiotemporal neural frame prediction. Hardware-efficient and latency-aware spatiotemporal neural frame prediction enables both frame generation and machine learning supersampling using a single network, rather than using separate networks for frame generation and supersampling.