公开(公告)号：US20240169542A1

公开(公告)日：2024-05-23

申请号：US18346470

申请日：2023-07-03

Applicant: QUALCOMM Incorporated

Inventor： Shubhankar Mangesh BORSE ,  Hyojin PARK ,  Risheek GARREPALLI ,  Debasmit DAS ,  Hong CAI ,  Fatih Murat PORIKLI

IPC: G06T7/10 ,  G06T5/20 ,  G06T5/50 ,  G06V10/44 ,  G06V10/80

CPC classification number: G06T7/10 ,  G06T5/20 ,  G06T5/50 ,  G06V10/44 ,  G06V10/806 ,  G06T2207/20221

Abstract: Techniques and systems are provided for generating one or more segmentations masks. For instance, a process may include generating a delta image based on a difference between a current image and a prior image. The process may further include processing, using a transform operation, the delta image and features representing the prior image to generate a transformed feature representation of the prior image. The process may include combining the transformed feature representation of the prior image with features representing the current image to generate a combined feature representation of the current image. The process may further include generating, based on the combined feature representation of the current image, a segmentation mask for the current image.

公开(公告)号：US20240144589A1

公开(公告)日：2024-05-02

申请号：US18177028

申请日：2023-03-01

Applicant: QUALCOMM Incorporated

Inventor： Minghua LIU ,  Yinhao ZHU ,  Hong CAI ,  Fatih Murat PORIKLI ,  Hao SU

IPC: G06T17/00 ,  G06T7/12 ,  G06V10/25 ,  G06V20/70

CPC classification number: G06T17/00 ,  G06T7/12 ,  G06V10/25 ,  G06V20/70 ,  G06T2207/10028 ,  G06V2201/07

Abstract: Systems and techniques are provided for part segmentation. For example, a process for performing part segmentation can include obtaining a three-dimensional capture of an object. The method can include generating one or more two-dimensional images of the object from the three-dimensional capture of the object. The method can further include processing the one or more two-dimensional images of the object to generate at least one two-dimensional bounding box associated with a part of the object. The method can include performing three-dimensional part segmentation of the part of the object based on a three-dimensional point cloud generated from the one or more two-dimensional images of the object and the at least one two-dimensional bounding box and based on semantically labeled super points which are merged into subgroups associated with the part of the object.

公开(公告)号：US20230298142A1

公开(公告)日：2023-09-21

申请号：US17655427

申请日：2022-03-18

Applicant: QUALCOMM Incorporated

Inventor： Jamie Menjay LIN ,  Diaa H J BADAWI ,  Hong CAI ,  Fatih Murat PORIKLI

IPC: G06T5/00 ,  G06T7/194 ,  G06T5/50

CPC classification number: G06T5/003 ,  G06T5/002 ,  G06T7/194 ,  G06T5/005 ,  G06T5/50 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Certain aspects of the present disclosure provide techniques for machine learning-based deblurring. An input image is received, and a deblurred image is generated based on the input image using a neural network, comprising: generating a feature tensor by processing the input image using a first portion of the neural network, generating a motion mask by processing the feature tensor using a motion portion of the neural network, and generating the deblurred image by processing the feature tensor and the motion mask using a deblur portion of the neural network.

公开(公告)号：US20250094793A1

公开(公告)日：2025-03-20

申请号：US18469909

申请日：2023-09-19

Applicant: QUALCOMM Incorporated

Inventor： Manish Kumar SINGH ,  Tianyu JIANG ,  Hsin-Pai CHENG ,  Kartikeya BHARDWAJ ,  Hong CAI ,  Mingu LEE ,  Munawar HAYAT ,  Christopher LOTT ,  Fatih Murat PORIKLI

IPC: G06N3/0499

Abstract: A processor-implemented method for image or text processing includes receiving, by an artificial neural network (ANN) model, a set of tokens corresponding to an input. A token interaction block of the ANN model processes the set of tokens according to each channel of the input to generate a spatial mixture of a set of features for each channel of the input. A feed forward network block of the ANN model generates a mixture of channel features based on the spatial mixture of the set of features for each channel of the input. An attention block of the ANN model determines a set of attended features of the mixture of channel features according to a set of attention weights. In turn, the ANN model generates an inference based on the set of attend features of the mixture of channel features.

公开(公告)号：US20240386650A1

公开(公告)日：2024-11-21

申请号：US18509113

申请日：2023-11-14

Applicant: QUALCOMM Incorporated

Inventor： Farhad GHAZVINIAN ZANJANI ,  Leyla MIRVAKHABOVA ,  Yinhao ZHU ,  Hong CAI ,  Fatih Murat PORIKLI

IPC: G06T15/06 ,  G06T7/10 ,  G06T7/50 ,  G06T15/10 ,  G06T17/20

Abstract: Systems and techniques are provided for processing image data corresponding to a scene. A process can include generating a planar distance map including a planar distance value for each pixel of at least one image corresponding to the scene. Planar segmentation is performed based on the planar distance map, a normal map corresponding to the at least one image, and positional encoding information of the planar distance map. A triangular mesh fragment is initialized based on sampling points from each planar segment of a plurality of planar segments from the planar segmentation. Ray-triangle intersections are determined based on performing ray casting for a reconstructed planar mesh including a plurality of triangular mesh fragments each corresponding to a different image. A planar reconstruction and segmentation machine learning network is optimized for the scene, based on training the planar reconstruction and segmentation machine learning network using one or more loss functions.

公开(公告)号：US20240171727A1

公开(公告)日：2024-05-23

申请号：US18470326

申请日：2023-09-19

Applicant: QUALCOMM Incorporated

Inventor： Yunxiao SHI ,  Hong CAI ,  Fatih Murat PORIKLI ,  Amin ANSARI ,  Sai Madhuraj JADHAV

IPC: H04N13/363 ,  G06T7/50 ,  G06V10/44 ,  G06V10/771 ,  H04N13/351

CPC classification number: H04N13/363 ,  G06T7/50 ,  G06V10/44 ,  G06V10/771 ,  H04N13/351 ,  G06V2201/07

Abstract: Systems and techniques are provided for processing image data. For example, a process can include obtaining a plurality of input images associated with a plurality of different spatial views. The process can include generating a set of features based on the plurality of input images. The process can include generating a set of projected features based on the set of features, wherein an embedding size associated with the set of projected features is smaller than an embedding size associated with the set of features. The process can include determining a cross-view attention associated with the plurality of different spatial views, the cross-view attention determined using the set of projected features.

公开(公告)号：US20230252658A1

公开(公告)日：2023-08-10

申请号：US17650027

申请日：2022-02-04

Applicant: QUALCOMM Incorporated

Inventor： Hong CAI ,  Shichong PENG ,  Janarbek MATAI ,  Jamie Menjay LIN ,  Debasmit DAS ,  Fatih Murat PORIKLI

IPC: G06T7/50 ,  G06T7/10 ,  G06N3/04

CPC classification number: G06T7/50 ,  G06T7/10 ,  G06N3/0454 ,  G06T2207/20084 ,  G06T2207/20212

Abstract: Certain aspects of the present disclosure provide techniques for generating fine depth maps for images of a scene based on semantic segmentation and segment-based refinement neural networks. An example method generally includes generating, through a segmentation neural network, a segmentation map based on an image of a scene. The segmentation map generally comprises a map segmenting the scene into a plurality of regions, and each region of the plurality of regions is generally associated with one of a plurality of categories. A first depth map of the scene is generated through a first depth neural network based on a depth measurement of the scene. A second depth map of the scene is generated through a depth refinement neural network based on the segmentation map and the first depth map. One or more actions are taken based on the second depth map of the scene.

公开(公告)号：US20230154005A1

公开(公告)日：2023-05-18

申请号：US17807614

申请日：2022-06-17

Applicant: QUALCOMM Incorporated

Inventor： Shubhankar Mangesh BORSE ,  Hyojin PARK ,  Hong CAI ,  Debasmit DAS ,  Risheek GARREPALLI ,  Fatih Murat PORIKLI

IPC: G06T7/10 ,  G06N3/08

CPC classification number: G06T7/10 ,  G06N3/08 ,  G06T2207/20084 ,  G06T2207/20081

Abstract: Aspects of the present disclosure relate to a novel framework for integrating both semantic and instance contexts for panoptic segmentation. In one example aspect, a method for processing image data includes: processing semantic feature data and instance feature data with a panoptic encoding generator to generate a panoptic encoding; processing the panoptic encoding to generate a panoptic segmentation features; and generating the panoptic segmentation mask based on the panoptic segmentation features.

公开(公告)号：US20230005165A1

公开(公告)日：2023-01-05

申请号：US17808520

申请日：2022-06-23

Applicant: QUALCOMM Incorporated

Inventor： Hong CAI ,  Janarbek MATAI ,  Shubhankar Mangesh BORSE ,  Yizhe ZHANG ,  Amin ANSARI ,  Fatih Murat PORIKLI

IPC: G06T7/50 ,  G06N3/08 ,  G06N3/04

Abstract: Certain aspects of the present disclosure provide techniques for cross-task distillation. A depth map is generated by processing an input image using a first machine learning model, and a segmentation map is generated by processing the depth map using a second machine learning model. A segmentation loss is computed based on the segmentation map and a ground-truth segmentation map, and the first machine learning model is refined based on the segmentation loss.

公开(公告)号：US20250166391A1

公开(公告)日：2025-05-22

申请号：US18585480

申请日：2024-02-23

Applicant: QUALCOMM Incorporated

Inventor： Shizhong Steve HAN ,  Hong CAI ,  Haiyan WANG ,  Yinhao ZHU ,  Yunxiao SHI ,  Fatih Murat PORIKLI ,  Sourab BAPU SRIDHAR ,  Senthil Kumar YOGAMANI

IPC: G06V20/58 ,  G06V10/10 ,  G06V10/84

Abstract: Certain aspects of the present disclosure provide techniques for performing 3D object detection. Such techniques may include obtaining one or more inputs associated with one or more two-dimensional (2D) views of a scene; selecting a set of 2D views of the scene from a plurality of 2D views of the scene based on the one or more inputs, the set of 2D views comprising a first 2D view of the scene and a second 2D view of the scene; and performing three-dimensional (3D) object detection in the scene based on the set of 2D views.