Deepak Sridhar

Title: Deepak Sridhar: Innovator in 3D Hand Pose Estimation

Introduction

Deepak Sridhar is a notable inventor based in San Diego, California. He has made significant contributions to the field of computer vision, particularly in the area of hand pose estimation. His innovative work has the potential to enhance various applications, including virtual reality and human-computer interaction.

Latest Patents

Deepak holds a patent titled "Methods and systems for 3D hand pose estimation from RGB images." This patent describes a sophisticated method for estimating a 3D hand pose using a 2D image that contains a detected hand. The process involves utilizing a U-net network to generate a global feature vector and a heatmap for the hand's keypoints. By concatenating information from these outputs, the system processes input tokens through a transformer encoder to derive a set of 2D keypoints. These keypoints are then used as queries in a transformer decoder to obtain additional 2D keypoints from a different view. Ultimately, the first and second sets of 2D keypoints are aggregated to produce a comprehensive set of estimated 3D keypoints.

Career Highlights

Deepak is currently employed at Huawei Technologies Co., Limited, where he continues to push the boundaries of technology. His work at Huawei allows him to collaborate with other talented professionals in the field, contributing to groundbreaking advancements in technology.

Collaborations

Some of Deepak's notable coworkers include Yannick Verdie and Zihao Yang. Their collaboration fosters an environment of innovation and creativity, leading to the development of cutting-edge technologies.

Conclusion

Deepak Sridhar's contributions to 3D hand pose estimation exemplify the impact of innovative thinking in technology. His patent and ongoing work at Huawei Technologies Co., Limited highlight his role as a key player in advancing computer vision applications.