公开(公告)号：US11880935B2

公开(公告)日：2024-01-23

申请号：US17951405

申请日：2022-09-23

Applicant: SHANGHAITECH UNIVERSITY

Inventor： Minye Wu ,  Jingyi Yu

IPC: G06T17/00 ,  G06V10/82 ,  G06F18/214 ,  G06F18/213 ,  G06T15/04 ,  G06T15/20 ,  G06T17/20 ,  G06V20/64 ,  G06T7/593 ,  H04N13/207

CPC classification number: G06T17/00 ,  G06F18/213 ,  G06F18/214 ,  G06T7/593 ,  G06T15/04 ,  G06T15/205 ,  G06T17/20 ,  G06V10/82 ,  G06V20/653 ,  H04N13/207 ,  G06T2200/08 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30196 ,  G06T2210/56

Abstract: An image-based method of modeling and rendering a three-dimensional model of an object is provided. The method comprises: obtaining a three-dimensional point cloud at each frame of a synchronized, multi-view video of an object, wherein the video comprises a plurality of frames; extracting a feature descriptor for each point in the point cloud for the plurality of frames without storing the feature descriptor for each frame; producing a two-dimensional feature map for a target camera; and using an anti-aliased convolutional neural network to decode the feature map into an image and a foreground mask.

公开(公告)号：US11880964B2

公开(公告)日：2024-01-23

申请号：US17074123

申请日：2020-10-19

Applicant: SHANGHAITECH UNIVERSITY

Inventor： Minye Wu ,  Zhiru Shi ,  Jingyi Yu

IPC: H04N5/225 ,  G06T5/50 ,  G06T7/593 ,  G06T7/557

CPC classification number: G06T5/50 ,  G06T7/557 ,  G06T7/596 ,  G06T2200/21 ,  G06T2207/10052

Abstract: A method of processing light field images for separating a transmitted layer from a reflection layer. The method comprises capturing a plurality of views at a plurality of viewpoints with different polarization angles; obtaining an initial disparity estimation for a first view using SIFT-flow, and warping the first view to a reference view; optimizing an objective function comprising a transmitted layer and a secondary layer using an Augmented Lagrange Multiplier (ALM) with Alternating Direction Minimizing (ADM) strategy; updating the disparity estimation for the first view; repeating the steps of optimizing the objective function and updating the disparity estimation until the change in the objective function between two consecutive iterations is below a threshold; and separating the transmitted layer and the secondary layer using the disparity estimation for the first view.

公开(公告)号：US11410459B2

公开(公告)日：2022-08-09

申请号：US16894032

申请日：2020-06-05

Applicant: SHANGHAITECH UNIVERSITY

Inventor： Zhiru Shi ,  Minye Wu ,  Wenguang Ma ,  Jingyi Yu

IPC: H04N5/225 ,  G06V20/64 ,  H04N13/00 ,  G06V40/16 ,  H04N13/282

Abstract: A method of detecting and recognizing faces using a light field camera array is provided. The method includes capturing multi-view color images using the light field camera array; obtaining a depth map; conducting light field rendering using a weight function comprising a depth component and a sematic component, where the weight function assigns a ray in the light field with a weight; and detecting and recognizing a face.