公开(公告)号：US20250166395A1

公开(公告)日：2025-05-22

申请号：US18585444

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: G06V20/64 ,  G06T7/30 ,  G06T15/00 ,  G06V10/75 ,  G06V10/80

Abstract: Certain aspects of the present disclosure provide techniques for performing 3D object detection. Such techniques may include obtaining a first set of features based on a first 2D view; obtaining a second set of features based on a second 2D view, obtaining a third set of features based on a third 2D view, obtaining a fourth set of features based on a fourth 2D view, wherein the first 2D view and the second 2D view are based on input from a first input sensor and the third 2D view and the fourth 2D view are based on input from a second input sensor. The techniques may also include performing cross-attention between the first set of features and the second set of features and between the third set of features and the fourth set of features; and performing 3D object detection.

公开(公告)号：US20250139733A1

公开(公告)日：2025-05-01

申请号：US18499604

申请日：2023-11-01

Applicant: QUALCOMM Incorporated

Inventor： Jisoo JEONG ,  Hong CAI ,  Risheek GARREPALLI ,  Jamie Menjay LIN ,  Munawar HAYAT ,  Fatih Murat PORIKLI

IPC: G06T3/00 ,  G06T5/50 ,  G06T7/20

Abstract: Systems and techniques described herein relate to generating an inter-frame from a first and second frame. An apparatus includes a memory storing a first frame and a second frame; and a processor coupled to the memory and configured to: estimate at least one optical flow between the first frame and the second frame; generate, based on the at least one optical flow, at least one occlusion mask; generate, based on the at least one optical flow and the at least one occlusion mask, at least one weighting mask; generate, based on the at least one optical flow and the at least one weighting mask, at least one inter-frame optical flow; generate, based on the at least one inter-frame optical flow and at least one of the first frame or the second frame, at least one warped frame; and generate, based on the at least one warped frame, an inter-frame.

公开(公告)号：US20250095182A1

公开(公告)日：2025-03-20

申请号：US18468656

申请日：2023-09-15

Applicant: QUALCOMM Incorporated

Inventor： Jisoo JEONG ,  Hong CAI ,  Babak EHTESHAMI BEJNORDI ,  Risheek GARREPALLI ,  Rajeev YASARLA ,  Fatih Murat PORIKLI

IPC: G06T7/593 ,  G06T7/246 ,  G06T7/285

Abstract: Techniques and systems are provided for image processing. For instance, a process can include correlating a first set of features from a first viewpoint with a second set of features from a second viewpoint at a first time period to generate a first disparity cost volume; correlating a third set of features from the first viewpoint at a second time period with the first set of features to generate a first optical flow cost volume; gating the first disparity cost volume to generate first intermediate disparity information; gating the first optical flow cost volume to generate first intermediate optical flow information; correlating the first set of features, the second set of features, and the first intermediate optical flow information to generate disparity information for output; and correlating the third set of features, the first set of features, and the first intermediate disparity information to generate optical flow information for output.

公开(公告)号：US20240161368A1

公开(公告)日：2024-05-16

申请号：US18460903

申请日：2023-09-05

Applicant: QUALCOMM Incorporated

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

IPC: G06T11/60 ,  G06T3/40 ,  G06T7/12 ,  G06T7/50 ,  G06V10/44

CPC classification number: G06T11/60 ,  G06T3/40 ,  G06T7/12 ,  G06T7/50 ,  G06V10/44

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for regenerative learning to enhance dense predictions. In one example method, an input image is accessed. A dense prediction output is generated based on the input image using a dense prediction machine learning (ML) model, and a regenerated version of the input image is generated. A first loss is generated based on the input image and a corresponding ground truth dense prediction, and a second loss is generated based on the regenerated version of the input image. One or more parameters of the dense prediction ML model are updated based on the first and second losses.

公开(公告)号：US20250148358A1

公开(公告)日：2025-05-08

申请号：US18504117

申请日：2023-11-07

Applicant: QUALCOMM Incorporated

Inventor： Zhuojin LI ,  Hsin-Pai CHENG ,  Hong CAI ,  Sweta PRIYADARSHI ,  Kartikeya BHARDWAJ ,  Viswanath GANAPATHY ,  Chirag Sureshbhai PATEL ,  Fatih Murat PORIKLI

IPC: G06N20/00

Abstract: A processor-implemented method for training-free architecture searching for a transformer model includes generating a set of transformer model candidates for a target device. Each transformer model candidate of the set of transformer model candidates is initialized with random weights. A set of data samples are randomly sampled to produce random data samples for inputting at each transformer model candidate. An attention confidence score is computed for each transformer model candidate based on the random data samples and the random weights. A transformer model candidate for the target device is selected based on the attention confidence score.

公开(公告)号：US20240177329A1

公开(公告)日：2024-05-30

申请号：US18481050

申请日：2023-10-04

Applicant: QUALCOMM Incorporated

Inventor： Hong CAI ,  Yinhao ZHU ,  Jisoo JEONG ,  Yunxiao SHI ,  Fatih Murat PORIKLI

IPC: G06T7/593 ,  G06T3/40 ,  G06T7/246 ,  G06T7/579

CPC classification number: G06T7/593 ,  G06T3/40 ,  G06T7/248 ,  G06T7/579 ,  G06T2207/10012 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Systems and techniques are provided for processing sensor data. For example, a process can include determining, using a trained machine learning system, a predicted depth map for an image, the predicted depth map including a respective predicted depth value for each pixel of the image. The process can further include obtaining depth values for the image, the depth values including depth values for less than all pixels of the image from a tracker configured to determine the depth values based on one or more feature points between frames. The process can further include scaling the predicted depth map for the image using and the depth values. The output of the process can be scale-correct depth prediction values.

公开(公告)号：US20240020848A1

公开(公告)日：2024-01-18

申请号：US18349771

申请日：2023-07-10

Applicant: QUALCOMM Incorporated

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

IPC: G06T7/168

CPC classification number: G06T7/168 ,  G06T2207/20132

Abstract: Systems and techniques are provided for processing one or more images. For instance, according to some aspects of the disclosure, a method may include obtaining an unlabeled image and generating at least one transformed image based on the unlabeled image. The method may include processing the unlabeled image using a pre-trained semantic segmentation model to generate a first segmentation output. The method may further include processing the at least one transformed image using the pre-trained semantic segmentation model to generate at least a second segmentation output. The method may include fine-tuning, based on the first segmentation output and at least the second segmentation output, one or more parameters of the pre-trained semantic segmentation model.

公开(公告)号：US20230004812A1

公开(公告)日：2023-01-05

申请号：US17808949

申请日：2022-06-24

Applicant: QUALCOMM Incorporated

Inventor： Shubhankar Mangesh BORSE ,  Hong CAI ,  Yizhe ZHANG ,  Fatih Murat PORIKLI

IPC: G06N3/08 ,  G06K9/62

Abstract: Certain aspects of the present disclosure provide techniques for training neural networks using hierarchical supervision. An example method generally includes training a neural network with a plurality of stages using a training data set and an initial number of classification clusters into which data in the training data set can be classified. A cluster-validation set performance metric is generated for each stage based on a reduced number of classification clusters relative to the initial number of classification clusters and a validation data set. A number of classification clusters to implement at each stage is selected based on the cluster-validation set performance metric and an angle selected relative to the cluster-validation set performance metric for a last stage of the neural network. The neural network is retrained based on the training data set and the selected number of classification clusters for each stage, and the trained neural network is deployed.

公开(公告)号：US20250148633A1

公开(公告)日：2025-05-08

申请号：US18666502

申请日：2024-05-16

Applicant: QUALCOMM Incorporated

Inventor： Rajeev YASARLA ,  Hong CAI ,  Risheek GARREPALLI ,  Yinhao ZHU ,  Jisoo JEONG ,  Yunxiao SHI ,  Manish Kumar SINGH ,  Fatih Murat PORIKLI

IPC: G06T7/593 ,  G06T7/20

Abstract: Systems and techniques are provided for generating depth information. For example, a process can include obtaining a first feature volume including visual features corresponding to each respective frame included in a first set of frames. A first query generator network can generate reconstruction features associated with a reconstructed feature volume corresponding to the first feature volume. Based on the first feature volume, a second query generator network can generate motion features associated with predicted future motion corresponding to the first feature volume. An initial depth prediction can be generated for each respective frame based on cross-attention between features of a depth prediction decoder, the reconstruction features, and the motion features. A refined depth prediction can be generated for each respective based on cross-attention between the initial depth prediction, the reconstruction features, and the motion features.

公开(公告)号：US20240303841A1

公开(公告)日：2024-09-12

申请号：US18538869

申请日：2023-12-13

Applicant: QUALCOMM Incorporated

Inventor： Rajeev YASARLA ,  Hong CAI ,  Jisoo JEONG ,  Risheek GARREPALLI ,  Yunxiao SHI ,  Fatih Murat PORIKLI

IPC: G06T7/50 ,  G06T7/246 ,  G06T11/60 ,  G06V10/44 ,  G06V10/62

CPC classification number: G06T7/50 ,  G06T7/246 ,  G06T11/60 ,  G06V10/44 ,  G06V10/62

Abstract: Disclosed are systems and techniques for capturing images (e.g., using a monocular image sensor) and detecting depth information. According to some aspects, a computing system or device can generate a feature representation of a current image and update accumulated feature information for storage in a memory based on a feature representation of a previous image and optical flow information of the previous image. The accumulated feature information can include accumulated image feature information associated with a plurality of previous images and accumulated optical flow information associated of the plurality of previous images. The computing system or device can obtain information associated with relative motion of the current image based on the accumulated feature information and the feature representation of the current image. The computing system or device can estimate depth information for the current image based on the information associated with the relative motion and the accumulated feature information.