公开(公告)号：US12033342B2

公开(公告)日：2024-07-09

申请号：US17203645

申请日：2021-03-16

申请人： Huan Liu ,  Zhixiang Chi ,  Yuanhao Yu ,  Yang Wang ,  Jin Tang

发明人： Huan Liu ,  Zhixiang Chi ,  Yuanhao Yu ,  Yang Wang ,  Jin Tang

IPC分类号： G06N3/0455 ,  G06F18/214 ,  G06N3/08 ,  G06T7/50 ,  G06T7/579 ,  G06V10/44

CPC分类号： G06T7/579 ,  G06F18/214 ,  G06N3/08 ,  G06V10/44 ,  G06T2207/10028 ,  G06T2207/20081

摘要： Systems, methods and computer-readable medium for predicting a depth for a video frame are disclosed. An example method may include steps of: receiving a plurality of training data, each comprising a set of consecutive video frames and a depth representation of a subsequent video frame to the consecutive video frames; receiving a pre-trained neural network model fθ having a plurality of weights θ; while the pre-trained neural network model fθ has not converged: computing a plurality of second weights θi′, based on each set of consecutive video frames, and updating the plurality of weights θ, based on the plurality of training data and the plurality of second weights θi′; receiving a plurality of new consecutive video frames with consecutive timestamps; and predicting a depth representation of video frame immediately subsequent to the new consecutive video frames based on the updated plurality of weights θ.

公开(公告)号：US20220156891A1

公开(公告)日：2022-05-19

申请号：US17098605

申请日：2020-11-16

申请人： Zhixiang Chi ,  Yang Wang ,  Yuanhao Yu ,  Jin Tang

发明人： Zhixiang Chi ,  Yang Wang ,  Yuanhao Yu ,  Jin Tang

IPC分类号： G06T5/00 ,  G06N3/08

摘要： Methods and systems for image deblurring are described. The weights of a deblurring network are first trained by meta-training the deblurring network on both a primary deblurring task and an auxiliary reconstruction task. Application-time training of the deblurring network is then performed, using an application-time blurry input image, to obtain values of application-time trained weights. Application-time training includes performing the auxiliary reconstruction task on the application-time blurry input image, and updating the weights of the deblurring network based on an auxiliary loss computed from the auxiliary reconstruction task. A deblurred output image is generated from the application-time blurry input image, using the application-time trained weights in the deblurring network.

公开(公告)号：US11741579B2

公开(公告)日：2023-08-29

申请号：US17098605

申请日：2020-11-16

申请人： Zhixiang Chi ,  Yang Wang ,  Yuanhao Yu ,  Jin Tang

发明人： Zhixiang Chi ,  Yang Wang ,  Yuanhao Yu ,  Jin Tang

IPC分类号： G06T5/00 ,  G06N3/08

CPC分类号： G06T5/003 ,  G06N3/08 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20201

摘要： Methods and systems for image deblurring are described. The weights of a deblurring network are first trained by meta-training the deblurring network on both a primary deblurring task and an auxiliary reconstruction task. Application-time training of the deblurring network is then performed, using an application-time blurry input image, to obtain values of application-time trained weights. Application-time training includes performing the auxiliary reconstruction task on the application-time blurry input image, and updating the weights of the deblurring network based on an auxiliary loss computed from the auxiliary reconstruction task. A deblurred output image is generated from the application-time blurry input image, using the application-time trained weights in the deblurring network.

公开(公告)号：US11778223B2

公开(公告)日：2023-10-03

申请号：US17406845

申请日：2021-08-19

申请人： Wentao Liu ,  Yuanhao Yu ,  Yang Wang ,  Juwei Lu ,  Xiaolin Wu ,  Jin Tang

发明人： Wentao Liu ,  Yuanhao Yu ,  Yang Wang ,  Juwei Lu ,  Xiaolin Wu ,  Jin Tang

IPC分类号： H04N19/59 ,  H04N19/51 ,  H04N19/184 ,  H04N19/136

CPC分类号： H04N19/51 ,  H04N19/136 ,  H04N19/184

摘要： A method, device and computer-readable medium for generating a super-resolution version of a compressed video stream. By leveraging the motion information and residual information in compressed video streams, described examples are able to skip the time-consuming motion-estimation step for most frames and make the most use of the SR results of key frames. A key frame SR module generates SR versions of I-frames and other key frames of a compressed video stream using techniques similar to existing multi-frame approaches to VSR. A non-key frame SR module generates SR version of the non-key inter frames between these key frames by making use of motion information and residual information used to encode the inter frames in the compressed video stream.

公开(公告)号：US11729395B2

公开(公告)日：2023-08-15

申请号：US17535840

申请日：2021-11-26

申请人： Sheral Sweta Kumar ,  Amartya Mukherjee ,  Seel Nimeshkumar Patel ,  Rui Xiang Chai ,  Wentao Liu ,  Yuanhao Yu ,  Yang Wang ,  Jin Tang

发明人： Sheral Sweta Kumar ,  Amartya Mukherjee ,  Seel Nimeshkumar Patel ,  Rui Xiang Chai ,  Wentao Liu ,  Yuanhao Yu ,  Yang Wang ,  Jin Tang

IPC分类号： H04N19/44 ,  H04N19/513 ,  H04N19/146 ,  H04N19/137 ,  H04N19/176 ,  H04N19/186 ,  H04N19/85

CPC分类号： H04N19/146 ,  H04N19/137 ,  H04N19/176 ,  H04N19/186 ,  H04N19/85

摘要： Devices and methods for extracting motion vector data during decoding compressed of video data are described. At a video decoder, an encoded video data for a frame of video from an input buffer is obtained. The encoded video data is decoded to obtain decoded image data for a decoded frame, where the decoding includes extracting corresponding motion vector data for the decoded frame. The decoded image data is stored in a temporary storage indexed with a given index, and the corresponding motion vector data is stored in a same or different temporary storage indexed with the given index. An output buffer indexed with the given index is filled with the decoded image data and the corresponding motion vector data stored in the respective temporary storage indexed with the given index.

公开(公告)号：US12062252B2

公开(公告)日：2024-08-13

申请号：US17538516

申请日：2021-11-30

申请人： Irina Kezele ,  Mostafa Shahabinejad ,  Seyed shahabeddin Nabavi ,  Wentao Liu ,  Yuanhao Yu ,  Rui Xiang Chai ,  Jin Tang ,  Yang Wang

发明人： Irina Kezele ,  Mostafa Shahabinejad ,  Seyed shahabeddin Nabavi ,  Wentao Liu ,  Yuanhao Yu ,  Rui Xiang Chai ,  Jin Tang ,  Yang Wang

IPC分类号： G06V40/20 ,  G06N5/04 ,  G06V10/62 ,  G06V10/778 ,  G06V10/94 ,  G06V30/19

CPC分类号： G06V40/20 ,  G06N5/04 ,  G06V10/62 ,  G06V10/778 ,  G06V10/94 ,  G06V30/1912 ,  G06V30/19127

摘要： Methods, devices and computer-readable media for processing a compressed video to perform an inference task are disclosed. Processing the compressed video may include selecting a subset of frame encodings of the compressed video, or zero or more modalities (RGB, motion vectors, residuals) of a frame encoding, for further processing to perform the inference task. Pre-existing motion vector and/or residual information in frame encodings of the compressed video are leveraged to adaptively and efficiently perform the inference task. In some embodiments, the inference task is an action recognition task, such as a human action recognition task.

公开(公告)号：US11810329B2

公开(公告)日：2023-11-07

申请号：US16953029

申请日：2020-11-19

申请人： Yuanhao Yu ,  Shuhao Li ,  Juwei Lu ,  Jin Tang

发明人： Yuanhao Yu ,  Shuhao Li ,  Juwei Lu ,  Jin Tang

IPC分类号： G06T7/90 ,  G06N3/084 ,  G06T7/521 ,  G06T7/557

CPC分类号： G06T7/90 ,  G06N3/084 ,  G06T7/521 ,  G06T7/557

摘要： Methods and systems for determining a surface color of a target surface under an environment with an environmental light source. A plurality of images of the target surface are captured as the target surface is illuminated with a variable intensity, constant color light source and a constant intensity, constant color environmental light source, wherein the intensity of the light source on the target surface is varied by a known amount between the capturing of the images. A color feature tensor, independent of the environmental light source, is extracted from the image data, and used to infer a surface color of the target surface.