公开(公告)号：US10360665B2

公开(公告)日：2019-07-23

申请号：US15898144

申请日：2018-02-15

Applicant: Tata Consultancy Services Limited

Inventor： Kavya Gupta ,  Brojeshwar Bhowmick ,  Angshul Majumdar

IPC: G06T5/00 ,  G06T9/00 ,  G06T1/20 ,  G06N3/04

Abstract: Motion blur occur when acquiring images and videos with cameras fitted to the high speed motion devices, for example, drones. Distorted images intervene with the mapping of the visual points, hence the pose estimation and tracking may get corrupted. System and method for solving inverse problems using a coupled autoencoder is disclosed. In an embodiment, solving inverse problems, for example, generating a clean sample from an unknown corrupted sample is disclosed. The coupled autoencoder learns the autoencoder weights and coupling map (between source and target) simultaneously. The technique is applicable to any transfer learning problem. The embodiments of the present disclosure implements/proposes a new formulation that recasts deblurring as a transfer learning problem which is solved using the proposed coupled autoencoder.

公开(公告)号：US11256962B2

公开(公告)日：2022-02-22

申请号：US16815206

申请日：2020-03-11

Applicant: Tata Consultancy Services Limited

Inventor： Sandika Biswas ,  Sanjana Sinha ,  Kavya Gupta ,  Brojeshwar Bhowmick

IPC: G06K9/00 ,  G06K9/62 ,  G06N3/08

Abstract: Estimating 3D human pose from monocular images is a challenging problem due to the variety and complexity of human poses and the inherent ambiguity in recovering depth from single view. Recent deep learning based methods show promising results by using supervised learning on 3D pose annotated datasets. However, the lack of large-scale 3D annotated training data makes the 3D pose estimation difficult in-the-wild. Embodiments of the present disclosure provide a method which can effectively predict 3D human poses from only 2D pose in a weakly-supervised manner by using both ground-truth 3D pose and ground-truth 2D pose based on re-projection error minimization as a constraint to predict the 3D joint locations. The method may further utilize additional geometric constraints on reconstructed body parts to regularize the pose in 3D along with minimizing re-projection error to improvise on estimating an accurate 3D pose.

公开(公告)号：US11216692B2

公开(公告)日：2022-01-04

申请号：US16502760

申请日：2019-07-03

Applicant: Tata Consultancy Services Limited

Inventor： Kavya Gupta ,  Brojeshwar Bhowmick ,  Angshul Majumdar

IPC: G06K9/62

Abstract: This disclosure relates to systems and methods for solving generic inverse problems by providing a coupled representation architecture using transform learning. Convention solutions are complex, require long training and testing times, reconstruction quality also may not be suitable for all applications. Furthermore, they preclude application to real-time scenarios due to the mentioned inherent lacunae. The methods provided herein require involve very low computational complexity with a need for only three matrix-vector products, and requires very short training and testing times, which makes it applicable for real-time applications. Unlike the conventional learning architectures using inductive approaches, the CASC of the present disclosure can learn directly from the source domain and the number of features in a source domain may not be necessarily equal to the number of features in a target domain.