Mar 2023 – Present · 3 yrs 3 mos · Bengaluru, Karnataka, India

• Leading the Visual Generative AI team for developing state-of-the-art generative modelling techniques based image restoration and enhancement solutions. E.g., Super Resolution, Weather and 24H Timelapse, Instruction based Image Editing.

Mar 2020 – Mar 2023 · 3 yrs · Bengaluru, Karnataka, India

Feb 2018 – Mar 2020 · 2 yrs 1 mo · Bengaluru, Karnataka, India

• I worked on scene understanding problems, particularly on depth estimation using deep learning techniques. I also mentored two interns while working along with them on stereo disparity estimation solution.
• I published and presented our work on stereo disparity estimation titled 'DISCO: Depth Inference from Stereo using Context' in IEEE International Conference on Multimedia and Expo (ICME) 2019. The paper was selected in top 15% for oral presentation.

Mar 2016 – Feb 2018 · 1 yr 11 mos · Bengaluru, Karnataka, India

• I worked on camera system framework in Android smartphones and several image processing solutions, such as shadow removal, glare detection in night images and single image haze removal using conditional adversarial generative networks (CGANs). I was also actively involved in idea generation process and filing patents.
• I published 3 papers (2 as first author and 1 in collaboration) on flash image shadow detection and removal, glare detection in night images and single image haze removal using CGANs. Our paper titled 'CANDY: Conditional Adversarial Networks based End-to-end System for Single Image Haze Removal' also won Meirt award in the global Samsung Best Paper Award Contest 2017. Only ~5.3% papers were awarded out of all the research papers submitted by Samsung researchers across the globe.
• I also won 2nd prize in the national level ideation contest 'Make Time' organized by Samsung Electronics. The idea was related to improving the user interaction in Samsung's Gear smartwatches.
• I contributed to the world's best open source computer vision library OpenCV.
• I got an opportunity to attend the Computer Vision Summer School at IIIT Hyderabad, where I was in the top-20% performers in the class (12th rank out of 126). The attendees were mostly PhD and MS graduates / students along with some industry experts.

Jun 2014 – Mar 2016 · 1 yr 9 mos · Bengaluru, Karnataka, India

• I worked on camera system framework in Android smartphones and several image processing solutions, such as shadow removal.
• I also published and presented our work on 'Flash Image Shadow Detection and Correction' solution in the 30th IEEE International Conference on Image and Vision Computing New Zealand (IVCNZ) 2015, held in Auckland, New Zealand.
• I proposed innovative ideas and implemented them. I was also involved in the development of mobile applications for Samsung's Tizen operating system.