Prakhar Kulshreshtha
Senior Applied Researcher at Geomagical Labs
Sunnyvale, California, United States
Summary
👤
Senior🎓
Top SchoolPrakhar Kulshreshtha is a Senior Applied Researcher with a decade of experience building computer vision and machine learning systems for real-world products, currently driving research at Geomagical Labs in Sunnyvale. He holds an MS in Computer Vision from Carnegie Mellon and has led applied projects ranging from SLAM-based long-term mapping with Amazon Lab126 to pathology image diagnostics at PathAI and a smartphone grain-assaying app at Samsung C-Lab. Comfortable bridging research and production, he has hands-on expertise in image/video processing, inpainting refinements (contributing to the well-known LaMa repository), and optimizing multi-scale inference pipelines. His background blends academic rigor—teaching and research at CMU—with industry impact, shipping CV solutions that target tangible user problems. Practical, product-minded, and curious, he often focuses on robustness in dynamic environments and resolution-agnostic model behavior.
10 years of coding experience
7 years of employment as a software developer
Indian Institute of Technology KanpurMaster of Science - MS Computer Vision, Master of Science - MS Computer Vision at Carnegie Mellon University
English, Hindi
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (12)
mask-rcnn10
faster-rcnn10
pytorch10
computer-vision10
tensor10
deep-learning10
tensorflow10
python10
model-optimization9
optimization9
optimisation9
generative-adversarial-network8
Programming languages (4)
Github contributions (5)
advimman/lama
Apr 2022 - Jul 2022
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
Role in this project:
ML Engineer
ML EngineerContributions:10 reviews, 6 commits, 2 PRs in 2 months
Contributions summary:Prakhar's contributions primarily focus on the refinement of the image inpainting process within the LaMa repository. Their commits involve modifications to the `refinement.py` file, which includes core components of the image inpainting algorithm. The changes touch upon multi-scale loss calculations, image downscaling, and the overall inference process, indicating an involvement in optimizing the inpainting pipeline and potentially improving its performance or stability. These modifications suggest an expertise in machine learning model refinement and optimization for computer vision tasks.
fouriercolabimage-inpaintinginpainting-methodsmask
geomagical/lama-with-refiner
May 2022 - Aug 2022
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
Contributions:14 commits, 2 PRs, 26 pushes in 2 months
pytorchmaskconvolutionsdeep-learninginpainting
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.