Kuldeep Kulkarni

I am a research scientist in Adobe Research, Bengaluru, India. Before that I did a post-doc stint at Carnegie Mellon University where I worked with Aswin Sankaranarayanan. I received my PhD in Electrical Engineering from Arizona State University under the supervision of Pavan Turaga. Prior to that, I received my undergraduate degree in Electrical Engineering from the National Institute of Technology Karnataka, Surathkal, India in 2009. I hail from Ilkal, a tiny little town in India, where I spent 18 wonderful years.

News: Our image animation technology, "Moving Elements", that is inspired by our CVPR 2022 paper is shipped to and is available in Adobe Photoshop Elements 2023.

Openings: I am looking for grad student interns who are passionate about becoming friends with pixels, for Spring/Summer 2024. Interested candidates may email me their resumes.

Email  /  Google Scholar  /  Resume  /  LinkedIn  /  Twitter  / 

Research

My current research interests are in the areas of computer vision, specifically image and video synthesis. Below are some selected projects I have worked on. For a more comprehensive set of publications and patents, please refer to my resume.

Blowing in the Wind: CycleNet for Human Cinemagraphs from Still Images
Hugo Bertiche, Niloy J. Mitra, Kuldeep Kulkarni, Chun-Hao Paul Huang, Tuanfeng Y. Wang, Meysam Madadi, Sergio Escalera, Duygu Ceylan
Computer Vision and Pattern Recognition (CVPR) 2023
Project Page
Self-supervised Multi-view Disentanglement for Expansion of Visual Collections
Praneetha Vaddamanu, Nihal Jain, Paridhi Maheshwari, Vishwa Vinay, Kuldeep Kulkarni
Web Search and Data Mining (WSDM) 2023
Code/Poster
GEMS: Scene Expansion using Generative Models of Graphs
Rishi Agarwal*, Tirupathi Saketh Chandra*, Vaidehi Patil*, Aniruddha Mahapatra*, Kuldeep Kulkarni, Vishwa Vinay
Winter Conference on Applications of Computer Vision (WACV) 2023
Paper/Poster
Controllable Animation of Fluid Elements in Still Images
Aniruddha Mahapatra, Kuldeep Kulkarni
Computer Vision and Pattern Recognition (CVPR) 2022
Project Page
SemIE: Semantically-aware Image Extrapolation
Bholeshwar Khurana, Soumya Ranjan Dash, Abhishek Bhatia, Aniruddha Mahapatra, Hrituraj Singh, Kuldeep Kulkarni
International Conference on Computer Vision (ICCV) 2021
Project Page
Halluci-Net: Scene Completion by Exploiting Object Co-occurrence Relationships
Kuldeep Kulkarni, Tejas Gokhale, Rajhans Singh, Pavan Turaga, Aswin Sankaranarayanan
AICC CVPR workshop 2021
Convolutional Neural Networks for Noniterative Reconstruction of Compressively Sensed Images
Suhas Lohit, Kuldeep Kulkarni, Ronan Kerviche, Pavan Turaga, Amit Ashok
IEEE Transactions on Computational Imaging 2018
Code
Weakly Supervised Learning of Heterogeneous Concepts in Videos
Sohil Shah, Kuldeep Kulkarni, Arijit Biswas, Ankit Gandhi, Om Deshmukh, Larry Davis
European Conference on Computer Vision (ECCV) 2016
Code/Poster
ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Measurements
Kuldeep Kulkarni, Suhas Lohit, Pavan Turaga, Ronan Kerviche, Amit Ashok
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
Project Page (Code available now).

This work was covered by 'Nuit Blanche'
Fast Integral Image Estimation at 1% measurement rate
Kuldeep Kulkarni, Pavan Turaga
under revisions at IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) , 2016
arXiv:1601.07258 [cs.CV]
Direct Inference on Compressive Measurements using Convolutional Neural Networks
Suhas Lohit, Kuldeep Kulkarni, Pavan Turaga
International Conference on Image Processing, 2016
Reconstruction-free action inference from compressive imagers
Kuldeep Kulkarni, Pavan Turaga
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)(Impact factor: 5.781, Accepted on July 31, 2015)
supplement

Reconstruction-free Inference on Compressive Measurements
Suhas Lohit, Kuldeep Kulkarni, Pavan Turaga, Jian Wang , Aswin Sankaranarayanan
4th IEEE Workshop on Computational Cameras and Displays (CCD), held in conjunction with IEEE CVPR, June 2015 (Best Paper Award)
Presentation

Recurrence Textures for Activity Recognition from compressive cameras
Kuldeep Kulkarni, Pavan Turaga
IEEE International Conference on Image Processing, 2012
Course Projects

What makes Federer look so elegant ?
Kuldeep Kulkarni, Vinay Venkataraman , December, 2013


Student and Intern Mentoring

This guy has graciously allowed me to use his super-cool website template :)